Home
last modified time | relevance | path

Searched refs:kswapd (Results 1 – 22 of 22) sorted by relevance

/linux/Documentation/translations/zh_CN/mm/
H A Dbalance.rst23 选项的机会主义高阶分配请求中。在这种情况下，调用者可能也希望避免唤醒kswapd。
54 所附的补丁实现了第二个解决方案。它还 “修复”了两个问题：首先，在低内存条件下，kswapd
59 kswapd还需要知道它应该平衡哪些区。kswapd主要是在无法进行平衡的情况下需要的，可能
61 kswapd并不真正需要平衡高内存区，因为中断上下文并不请求高内存页。kswapd看zone
71 请求中设置了GFP_WAIT）。与此相反的是，决定唤醒kswapd以释放一些区的页。这个决定不是基于
H A Dphysical_memory.rst265 ``kswapd``
266 每个节点的kswapd内核线程实例。
275 控制kswapd尝试回收的order。
278 kswapd线程可以回收的最高区域索引。
281 kswapd无法回收任何页面的运行次数。
/linux/Documentation/mm/
H A Dbalance.rst15 the caller may also wish to avoid waking kswapd.
64 problems: first, kswapd is woken up as in 2.2 on low memory conditions
72 kswapd also needs to know about the zones it should balance. kswapd is
75 and all process contexts are sleeping. For 2.3, kswapd does not really
77 highmem pages. kswapd looks at the zone_wake_kswapd field in the zone
90 Orthogonal to this, is the decision to poke kswapd to free some zone pages.
H A Dphysical_memory.rst278 ``kswapd``
279 Per-node instance of kswapd kernel thread.
291 Controls the order kswapd tries to reclaim
294 The highest zone index to be reclaimed by kswapd
297 Number of runs kswapd was unable to reclaim any pages
384 When the amount of free pages in a zone is below the low watermark, kswapd is
386 kswapd stops reclaiming (a zone is balanced) when the
389 the amount of free pages in a zone is above the promo watermark, kswapd stops
399 pressure to reduce the likelihood of future fallbacks and wake kswapd now
400 as the node may be balanced overall and kswapd will not wake naturally.
[all …]
H A Dmultigen_lru.rst9 memory. It directly impacts the kswapd CPU usage and RAM efficiency.
/linux/Documentation/translations/zh_CN/core-api/
H A Dmemory-allocation.rst86 试图从当前上下文中释放内存，但如果该区域低于低水位，可以唤醒kswapd来回收内存。可
/linux/Documentation/translations/zh_TW/admin-guide/mm/damon/
H A Dreclaim.rst24 有助於節省內存和減少延遲高峯，這些延遲是由直接回收進程或kswapd的CPU消耗引起的，同時只產
/linux/Documentation/translations/zh_CN/admin-guide/mm/damon/
H A Dreclaim.rst24 有助于节省内存和减少延迟高峰，这些延迟是由直接回收进程或kswapd的CPU消耗引起的，同时只产
/linux/mm/
H A Dvmscan.c7326 static int kswapd(void *p) in kswapd() function
7499 if (!pgdat->kswapd) { in kswapd_run()
7500 pgdat->kswapd = kthread_create_on_node(kswapd, pgdat, nid, "kswapd%d", nid); in kswapd_run()
7501 if (IS_ERR(pgdat->kswapd)) { in kswapd_run()
7504 nid, PTR_ERR(pgdat->kswapd)); in kswapd_run()
7506 pgdat->kswapd = NULL; in kswapd_run()
7508 wake_up_process(pgdat->kswapd); in kswapd_run()
7521 struct task_struct *kswapd; in kswapd_stop() local
7524 kswapd = pgdat->kswapd; in kswapd_stop()
7525 if (kswapd) { in kswapd_stop()
[all …]
H A Dcompaction.c2157 running = pgdat->kswapd && task_is_running(pgdat->kswapd); in kswapd_is_running()
/linux/Documentation/admin-guide/sysctl/
H A Dvm.rst1073 This factor controls the aggressiveness of kswapd. It defines the
1074 amount of memory left in a node/system before kswapd is woken up and
1075 how much memory needs to be free before kswapd goes back to sleep.
1081 A high rate of threads entering direct reclaim (allocstall) or kswapd
1083 that the number of free pages kswapd maintains for latency reasons is
1085 can then be used to tune kswapd aggressiveness accordingly.
/linux/Documentation/admin-guide/mm/
H A Dmultigen_lru.rst9 memory. It directly impacts the kswapd CPU usage and RAM efficiency.
H A Dconcepts.rst185 allocation request will awaken the ``kswapd`` daemon. It will
H A Dtranshuge.rst177 means that an application will wake kswapd in the background
185 other regions will wake kswapd in the background to reclaim
/linux/Documentation/core-api/
H A Dmemory-allocation.rst102 context but can wake kswapd to reclaim memory if the zone is below
/linux/Documentation/admin-guide/mm/damon/
H A Dreclaim.rst17 reclaim of the process or CPU consumption of kswapd, while incurring only
/linux/Documentation/admin-guide/cgroup-v1/
H A Dmemory.rst223 unmapped (by kswapd), they may exist as SwapCache in the system until they
268 The global LRU(kswapd) can swap out arbitrary pages. Swap-out means
729 it gets invoked from balance_pgdat (kswapd).
/linux/include/linux/
H A Dmmzone.h1439 struct task_struct *kswapd; /* Protected by kswapd_lock */ member
/linux/Documentation/arch/x86/
H A Dsgx.rst163 Similar to the core kswapd, ksgxd, is responsible for managing the
/linux/fs/xfs/libxfs/
H A Dxfs_btree.c2997 bool kswapd; /* allocation in kswapd context */ member
3020 if (args->kswapd) in xfs_btree_split_worker()
3081 args.kswapd = current_is_kswapd(); in xfs_btree_split()
/linux/Documentation/admin-guide/
H A Dcgroup-v2.rst1676 Amount of scanned pages by kswapd (in an inactive LRU list)
1688 Amount of reclaimed pages by kswapd
1768 Number of pages demoted by kswapd.
/linux/
H A DCREDITS3412 D: kswapd fixes, random kernel hacker, rmap VM,