forked from mirrors/linux
ad6b26b6a0
On systems with NUMA balancing enabled, it has been found that tracking
task activities resulting from NUMA balancing is beneficial. NUMA
balancing employs two mechanisms for task migration: one is to migrate
a task to an idle CPU within its preferred node, and the other is to
swap tasks located on different nodes when they are on each other's
preferred nodes.
The kernel already provides NUMA page migration statistics in
/sys/fs/cgroup/mytest/memory.stat and /proc/{PID}/sched. However, it
lacks statistics regarding task migration and swapping. Therefore,
relevant counts for task migration and swapping should be added.
The following two new fields:
numa_task_migrated
numa_task_swapped
will be shown in /sys/fs/cgroup/{GROUP}/memory.stat, /proc/{PID}/sched
and /proc/vmstat.
Introducing both per-task and per-memory cgroup (memcg) NUMA balancing
statistics facilitates a rapid evaluation of the performance and
resource utilization of the target workload. For instance, users can
first identify the container with high NUMA balancing activity and then
further pinpoint a specific task within that group, and subsequently
adjust the memory policy for that task. In short, although it is
possible to iterate through /proc/$pid/sched to locate the problematic
task, the introduction of aggregated NUMA balancing activity for tasks
within each memcg can assist users in identifying the task more
efficiently through a divide-and-conquer approach.
As Libo Chen pointed out, the memcg event relies on the text names in
vmstat_text, and /proc/vmstat generates corresponding items based on
vmstat_text. Thus, the relevant task migration and swapping events
introduced in vmstat_text also need to be populated by
count_vm_numa_event(), otherwise these values are zero in /proc/vmstat.
In theory, task migration and swap events are part of the scheduler's
activities. The reason for exposing them through the
memory.stat/vmstat interface is that we already have NUMA balancing
statistics in memory.stat/vmstat, and these events are closely related
to each other. Following Shakeel's suggestion, we describe the
end-to-end flow/story of all these events occurring on a timeline for
future reference:
The goal of NUMA balancing is to co-locate a task and its memory pages
on the same NUMA node. There are two strategies: migrate the pages to
the task's node, or migrate the task to the node where its pages
reside.
Suppose a task p1 is running on Node 0, but its pages are located on
Node 1. NUMA page fault statistics for p1 reveal its "page footprint"
across nodes. If NUMA balancing detects that most of p1's pages are on
Node 1:
1.Page Migration Attempt:
The Numa balance first tries to migrate p1's pages to Node 0.
The numa_page_migrate counter increments.
2.Task Migration Strategies:
After the page migration finishes, Numa balance checks every
1 second to see if p1 can be migrated to Node 1.
Case 2.1: Idle CPU Available
If Node 1 has an idle CPU, p1 is directly scheduled there. This
event is logged as numa_task_migrated.
Case 2.2: No Idle CPU (Task Swap)
If all CPUs on Node1 are busy, direct migration could cause CPU
contention or load imbalance. Instead: The Numa balance selects a
candidate task p2 on Node 1 that prefers Node 0 (e.g., due to its own
page footprint). p1 and p2 are swapped. This cross-node swap is
recorded as numa_task_swapped.
Link: https://lkml.kernel.org/r/d00edb12ba0f0de3c5222f61487e65f2ac58f5b1.1748493462.git.yu.c.chen@intel.com
Link: https://lkml.kernel.org/r/7ef90a88602ed536be46eba7152ed0d33bad5790.1748002400.git.yu.c.chen@intel.com
Signed-off-by: Chen Yu <yu.c.chen@intel.com>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Tested-by: Madadi Vineeth Reddy <vineethr@linux.ibm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Cc: Aubrey Li <aubrey.li@intel.com>
Cc: Ayush Jain <Ayush.jain3@amd.com>
Cc: "Chen, Tim C" <tim.c.chen@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Libo Chen <libo.chen@oracle.com>
Cc: Mel Gorman <mgorman <mgorman@suse.de>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Michal Koutný <mkoutny@suse.com>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
201 lines
4.4 KiB
C
201 lines
4.4 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#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
|
|
|
|
#ifdef CONFIG_ZONE_DEVICE
|
|
#define DEVICE_ZONE(xx) xx##_DEVICE,
|
|
#else
|
|
#define DEVICE_ZONE(xx)
|
|
#endif
|
|
|
|
#define FOR_ALL_ZONES(xx) DMA_ZONE(xx) DMA32_ZONE(xx) xx##_NORMAL, \
|
|
HIGHMEM_ZONE(xx) xx##_MOVABLE, DEVICE_ZONE(xx)
|
|
|
|
enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
|
|
FOR_ALL_ZONES(PGALLOC)
|
|
FOR_ALL_ZONES(ALLOCSTALL)
|
|
FOR_ALL_ZONES(PGSCAN_SKIP)
|
|
PGFREE, PGACTIVATE, PGDEACTIVATE, PGLAZYFREE,
|
|
PGFAULT, PGMAJFAULT,
|
|
PGLAZYFREED,
|
|
PGREFILL,
|
|
PGREUSE,
|
|
PGSTEAL_KSWAPD,
|
|
PGSTEAL_DIRECT,
|
|
PGSTEAL_KHUGEPAGED,
|
|
PGSTEAL_PROACTIVE,
|
|
PGSCAN_KSWAPD,
|
|
PGSCAN_DIRECT,
|
|
PGSCAN_KHUGEPAGED,
|
|
PGSCAN_PROACTIVE,
|
|
PGSCAN_DIRECT_THROTTLE,
|
|
PGSCAN_ANON,
|
|
PGSCAN_FILE,
|
|
PGSTEAL_ANON,
|
|
PGSTEAL_FILE,
|
|
#ifdef CONFIG_NUMA
|
|
PGSCAN_ZONE_RECLAIM_SUCCESS,
|
|
PGSCAN_ZONE_RECLAIM_FAILED,
|
|
#endif
|
|
PGINODESTEAL, SLABS_SCANNED, KSWAPD_INODESTEAL,
|
|
KSWAPD_LOW_WMARK_HIT_QUICKLY, KSWAPD_HIGH_WMARK_HIT_QUICKLY,
|
|
PAGEOUTRUN, PGROTATED,
|
|
DROP_PAGECACHE, DROP_SLAB,
|
|
OOM_KILL,
|
|
#ifdef CONFIG_NUMA_BALANCING
|
|
NUMA_PTE_UPDATES,
|
|
NUMA_HUGE_PTE_UPDATES,
|
|
NUMA_HINT_FAULTS,
|
|
NUMA_HINT_FAULTS_LOCAL,
|
|
NUMA_PAGE_MIGRATE,
|
|
NUMA_TASK_MIGRATE,
|
|
NUMA_TASK_SWAP,
|
|
#endif
|
|
#ifdef CONFIG_MIGRATION
|
|
PGMIGRATE_SUCCESS, PGMIGRATE_FAIL,
|
|
THP_MIGRATION_SUCCESS,
|
|
THP_MIGRATION_FAIL,
|
|
THP_MIGRATION_SPLIT,
|
|
#endif
|
|
#ifdef CONFIG_COMPACTION
|
|
COMPACTMIGRATE_SCANNED, COMPACTFREE_SCANNED,
|
|
COMPACTISOLATED,
|
|
COMPACTSTALL, COMPACTFAIL, COMPACTSUCCESS,
|
|
KCOMPACTD_WAKE,
|
|
KCOMPACTD_MIGRATE_SCANNED, KCOMPACTD_FREE_SCANNED,
|
|
#endif
|
|
#ifdef CONFIG_HUGETLB_PAGE
|
|
HTLB_BUDDY_PGALLOC, HTLB_BUDDY_PGALLOC_FAIL,
|
|
#endif
|
|
#ifdef CONFIG_CMA
|
|
CMA_ALLOC_SUCCESS,
|
|
CMA_ALLOC_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_FAULT_FALLBACK_CHARGE,
|
|
THP_COLLAPSE_ALLOC,
|
|
THP_COLLAPSE_ALLOC_FAILED,
|
|
THP_FILE_ALLOC,
|
|
THP_FILE_FALLBACK,
|
|
THP_FILE_FALLBACK_CHARGE,
|
|
THP_FILE_MAPPED,
|
|
THP_SPLIT_PAGE,
|
|
THP_SPLIT_PAGE_FAILED,
|
|
THP_DEFERRED_SPLIT_PAGE,
|
|
THP_UNDERUSED_SPLIT_PAGE,
|
|
THP_SPLIT_PMD,
|
|
THP_SCAN_EXCEED_NONE_PTE,
|
|
THP_SCAN_EXCEED_SWAP_PTE,
|
|
THP_SCAN_EXCEED_SHARED_PTE,
|
|
#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
|
|
THP_SPLIT_PUD,
|
|
#endif
|
|
THP_ZERO_PAGE_ALLOC,
|
|
THP_ZERO_PAGE_ALLOC_FAILED,
|
|
THP_SWPOUT,
|
|
THP_SWPOUT_FALLBACK,
|
|
#endif
|
|
#ifdef CONFIG_MEMORY_BALLOON
|
|
BALLOON_INFLATE,
|
|
BALLOON_DEFLATE,
|
|
#ifdef CONFIG_BALLOON_COMPACTION
|
|
BALLOON_MIGRATE,
|
|
#endif
|
|
#endif
|
|
#ifdef CONFIG_DEBUG_TLBFLUSH
|
|
NR_TLB_REMOTE_FLUSH, /* cpu tried to flush others' tlbs */
|
|
NR_TLB_REMOTE_FLUSH_RECEIVED,/* cpu received ipi for flush */
|
|
NR_TLB_LOCAL_FLUSH_ALL,
|
|
NR_TLB_LOCAL_FLUSH_ONE,
|
|
#endif /* CONFIG_DEBUG_TLBFLUSH */
|
|
#ifdef CONFIG_SWAP
|
|
SWAP_RA,
|
|
SWAP_RA_HIT,
|
|
SWPIN_ZERO,
|
|
SWPOUT_ZERO,
|
|
#ifdef CONFIG_KSM
|
|
KSM_SWPIN_COPY,
|
|
#endif
|
|
#endif
|
|
#ifdef CONFIG_KSM
|
|
COW_KSM,
|
|
#endif
|
|
#ifdef CONFIG_ZSWAP
|
|
ZSWPIN,
|
|
ZSWPOUT,
|
|
ZSWPWB,
|
|
#endif
|
|
#ifdef CONFIG_X86
|
|
DIRECT_MAP_LEVEL2_SPLIT,
|
|
DIRECT_MAP_LEVEL3_SPLIT,
|
|
DIRECT_MAP_LEVEL2_COLLAPSE,
|
|
DIRECT_MAP_LEVEL3_COLLAPSE,
|
|
#endif
|
|
#ifdef CONFIG_PER_VMA_LOCK_STATS
|
|
VMA_LOCK_SUCCESS,
|
|
VMA_LOCK_ABORT,
|
|
VMA_LOCK_RETRY,
|
|
VMA_LOCK_MISS,
|
|
#endif
|
|
#ifdef CONFIG_DEBUG_STACK_USAGE
|
|
KSTACK_1K,
|
|
#if THREAD_SIZE > 1024
|
|
KSTACK_2K,
|
|
#endif
|
|
#if THREAD_SIZE > 2048
|
|
KSTACK_4K,
|
|
#endif
|
|
#if THREAD_SIZE > 4096
|
|
KSTACK_8K,
|
|
#endif
|
|
#if THREAD_SIZE > 8192
|
|
KSTACK_16K,
|
|
#endif
|
|
#if THREAD_SIZE > 16384
|
|
KSTACK_32K,
|
|
#endif
|
|
#if THREAD_SIZE > 32768
|
|
KSTACK_64K,
|
|
#endif
|
|
#if THREAD_SIZE > 65536
|
|
KSTACK_REST,
|
|
#endif
|
|
#endif /* CONFIG_DEBUG_STACK_USAGE */
|
|
NR_VM_EVENT_ITEMS
|
|
};
|
|
|
|
#ifndef CONFIG_TRANSPARENT_HUGEPAGE
|
|
#define THP_FILE_ALLOC ({ BUILD_BUG(); 0; })
|
|
#define THP_FILE_FALLBACK ({ BUILD_BUG(); 0; })
|
|
#define THP_FILE_FALLBACK_CHARGE ({ BUILD_BUG(); 0; })
|
|
#define THP_FILE_MAPPED ({ BUILD_BUG(); 0; })
|
|
#endif
|
|
|
|
#endif /* VM_EVENT_ITEM_H_INCLUDED */
|