mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-26 04:50:52 +07:00
72403b4a0f
Commit 0255d49184 ("mm: Account for a THP NUMA hinting update as one
PTE update") was added to account for the number of PTE updates when
marking pages prot_numa. task_numa_work was using the old return value
to track how much address space had been updated. Altering the return
value causes the scanner to do more work than it is configured or
documented to in a single unit of work.
This patch reverts that commit and accounts for the number of THP
updates separately in vmstat. It is up to the administrator to
interpret the pair of values correctly. This is a straight-forward
operation and likely to only be of interest when actively debugging NUMA
balancing problems.
The impact of this patch is that the NUMA PTE scanner will scan slower
when THP is enabled and workloads may converge slower as a result. On
the flip size system CPU usage should be lower than recent tests
reported. This is an illustrative example of a short single JVM specjbb
test
specjbb
3.12.0 3.12.0
vanilla acctupdates
TPut 1 26143.00 ( 0.00%) 25747.00 ( -1.51%)
TPut 7 185257.00 ( 0.00%) 183202.00 ( -1.11%)
TPut 13 329760.00 ( 0.00%) 346577.00 ( 5.10%)
TPut 19 442502.00 ( 0.00%) 460146.00 ( 3.99%)
TPut 25 540634.00 ( 0.00%) 549053.00 ( 1.56%)
TPut 31 512098.00 ( 0.00%) 519611.00 ( 1.47%)
TPut 37 461276.00 ( 0.00%) 474973.00 ( 2.97%)
TPut 43 403089.00 ( 0.00%) 414172.00 ( 2.75%)
3.12.0 3.12.0
vanillaacctupdates
User 5169.64 5184.14
System 100.45 80.02
Elapsed 252.75 251.85
Performance is similar but note the reduction in system CPU time. While
this showed a performance gain, it will not be universal but at least
it'll be behaving as documented. The vmstats are obviously different but
here is an obvious interpretation of them from mmtests.
3.12.0 3.12.0
vanillaacctupdates
NUMA page range updates 1408326 11043064
NUMA huge PMD updates 0 21040
NUMA PTE updates 1408326 291624
"NUMA page range updates" == nr_pte_updates and is the value returned to
the NUMA pte scanner. NUMA huge PMD updates were the number of THP
updates which in combination can be used to calculate how many ptes were
updated from userspace.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reported-by: Alex Thorlton <athorlton@sgi.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
84 lines
2.2 KiB
C
84 lines
2.2 KiB
C
#ifndef VM_EVENT_ITEM_H_INCLUDED
|
|
#define VM_EVENT_ITEM_H_INCLUDED
|
|
|
|
#ifdef CONFIG_ZONE_DMA
|
|
#define DMA_ZONE(xx) xx##_DMA,
|
|
#else
|
|
#define DMA_ZONE(xx)
|
|
#endif
|
|
|
|
#ifdef CONFIG_ZONE_DMA32
|
|
#define DMA32_ZONE(xx) xx##_DMA32,
|
|
#else
|
|
#define DMA32_ZONE(xx)
|
|
#endif
|
|
|
|
#ifdef CONFIG_HIGHMEM
|
|
#define HIGHMEM_ZONE(xx) , xx##_HIGH
|
|
#else
|
|
#define HIGHMEM_ZONE(xx)
|
|
#endif
|
|
|
|
#define FOR_ALL_ZONES(xx) DMA_ZONE(xx) DMA32_ZONE(xx) xx##_NORMAL HIGHMEM_ZONE(xx) , xx##_MOVABLE
|
|
|
|
enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
|
|
FOR_ALL_ZONES(PGALLOC),
|
|
PGFREE, PGACTIVATE, PGDEACTIVATE,
|
|
PGFAULT, PGMAJFAULT,
|
|
FOR_ALL_ZONES(PGREFILL),
|
|
FOR_ALL_ZONES(PGSTEAL_KSWAPD),
|
|
FOR_ALL_ZONES(PGSTEAL_DIRECT),
|
|
FOR_ALL_ZONES(PGSCAN_KSWAPD),
|
|
FOR_ALL_ZONES(PGSCAN_DIRECT),
|
|
PGSCAN_DIRECT_THROTTLE,
|
|
#ifdef CONFIG_NUMA
|
|
PGSCAN_ZONE_RECLAIM_FAILED,
|
|
#endif
|
|
PGINODESTEAL, SLABS_SCANNED, KSWAPD_INODESTEAL,
|
|
KSWAPD_LOW_WMARK_HIT_QUICKLY, KSWAPD_HIGH_WMARK_HIT_QUICKLY,
|
|
PAGEOUTRUN, ALLOCSTALL, PGROTATED,
|
|
#ifdef CONFIG_NUMA_BALANCING
|
|
NUMA_PTE_UPDATES,
|
|
NUMA_HUGE_PTE_UPDATES,
|
|
NUMA_HINT_FAULTS,
|
|
NUMA_HINT_FAULTS_LOCAL,
|
|
NUMA_PAGE_MIGRATE,
|
|
#endif
|
|
#ifdef CONFIG_MIGRATION
|
|
PGMIGRATE_SUCCESS, PGMIGRATE_FAIL,
|
|
#endif
|
|
#ifdef CONFIG_COMPACTION
|
|
COMPACTMIGRATE_SCANNED, COMPACTFREE_SCANNED,
|
|
COMPACTISOLATED,
|
|
COMPACTSTALL, COMPACTFAIL, COMPACTSUCCESS,
|
|
#endif
|
|
#ifdef CONFIG_HUGETLB_PAGE
|
|
HTLB_BUDDY_PGALLOC, HTLB_BUDDY_PGALLOC_FAIL,
|
|
#endif
|
|
UNEVICTABLE_PGCULLED, /* culled to noreclaim list */
|
|
UNEVICTABLE_PGSCANNED, /* scanned for reclaimability */
|
|
UNEVICTABLE_PGRESCUED, /* rescued from noreclaim list */
|
|
UNEVICTABLE_PGMLOCKED,
|
|
UNEVICTABLE_PGMUNLOCKED,
|
|
UNEVICTABLE_PGCLEARED, /* on COW, page truncate */
|
|
UNEVICTABLE_PGSTRANDED, /* unable to isolate on unlock */
|
|
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
|
|
THP_FAULT_ALLOC,
|
|
THP_FAULT_FALLBACK,
|
|
THP_COLLAPSE_ALLOC,
|
|
THP_COLLAPSE_ALLOC_FAILED,
|
|
THP_SPLIT,
|
|
THP_ZERO_PAGE_ALLOC,
|
|
THP_ZERO_PAGE_ALLOC_FAILED,
|
|
#endif
|
|
#ifdef CONFIG_SMP
|
|
NR_TLB_REMOTE_FLUSH, /* cpu tried to flush others' tlbs */
|
|
NR_TLB_REMOTE_FLUSH_RECEIVED,/* cpu received ipi for flush */
|
|
#endif
|
|
NR_TLB_LOCAL_FLUSH_ALL,
|
|
NR_TLB_LOCAL_FLUSH_ONE,
|
|
NR_VM_EVENT_ITEMS
|
|
};
|
|
|
|
#endif /* VM_EVENT_ITEM_H_INCLUDED */
|