Lines Matching +full:fine +full:- +full:tuning
20 - The physical memory available to a machine can be adjusted at runtime, up- or
25 - Replacing hardware, such as DIMMs or whole NUMA nodes, without downtime. One
28 - Reducing energy consumption either by physically unplugging memory modules or
32 used to expose persistent memory, other performance-differentiated memory and
39 ------------------------------
54 ------------------------
71 --------------------------
94 ------------------
112 --------------
152 -------------------------------
154 If auto-onlining of memory blocks isn't enabled, user-space has to manually
183 ------------------------------------
185 The kernel can be configured to try auto-onlining of newly added memory blocks.
189 The configured auto-online behavior can be observed via::
193 Auto-onlining can be enabled by writing ``online``, ``online_kernel`` or
201 Modifying the auto-online behavior will only affect all subsequently added
206 In corner cases, auto-onlining can fail. The kernel won't retry. Note that
207 auto-onlining is not expected to fail in default configurations.
215 -----------------------
248 ------------------------------------
250 The state (online/offline/going-offline) of a memory block can be observed
270 ------------------------------------------
279 ``auto_online_blocks`` read-write: set or get the default state of new memory
280 blocks; configure auto-onlining.
287 ``block_size_bytes`` read-only: the size in bytes of a memory block.
288 ``probe`` write-only: add (probe) selected memory blocks manually
293 ``uevent`` read-write: generic udev file for device subsystems.
294 ``crash_hotplug`` read-only: when changes to the system memory map
314 ------------------------------------
339 ``online`` read-write: simplified interface to trigger onlining /
342 ``phys_device`` read-only: legacy interface only ever used on s390x to
344 ``phys_index`` read-only: the memory block id (XXX).
345 ``removable`` read-only: legacy interface that indicated whether a memory
349 ``state`` read-write: advanced interface to trigger onlining /
360 When reading, ``online``, ``offline`` and ``going-offline``
362 ``uevent`` read-write: generic uevent file for devices.
363 ``valid_zones`` read-only: when a block is online, shows the zone it
390 /sys/devices/system/node/node0/memory9 -> ../../memory/memory9
394 /sys/devices/system/memory/memory9/node0 -> ../../node/node0
397 -----------------------
403 ``memhp_default_state`` configure auto-onlining by essentially setting
406 using the ``contig-zones`` online policy. When
412 See Documentation/admin-guide/kernel-parameters.txt for a more generic
416 ------------------
432 ``memmap_on_memory`` read-write: Allocate memory for the memmap from
457 ``online_policy`` read-write: Set the basic policy used for
460 ``contig-zones`` has been the kernel default
466 When set to ``contig-zones``, the kernel will
474 When set to ``auto-movable``, the kernel will
488 firmware-provided memory map early during boot
491 done by virtio-mem or by some hypervisors
497 belonging to a virtio-mem device will be
499 special-casing units of memory blocks that can
505 ``auto_movable_ratio`` read-write: Set the maximum MOVABLE:KERNEL
506 memory ratio in % for the ``auto-movable``
533 hotplugged by a virtio-mem device that got
536 virtio-mem device.
537 ``auto_movable_numa_aware`` read-write: Configure whether the
538 ``auto_movable_ratio`` in the ``auto-movable``
572 ---------------
579 Usually, MOVABLE:KERNEL ratios of up to 3:1 or even 4:1 are fine. Ratios of 63:1
583 long-term pinning of pages, might not be able to deal with ZONE_MOVABLE at all.
592 ----------------------------------
596 the normal case, ZONE_MOVABLE can be used when allocating such pages just fine.
600 ZONE_MOVABLE, especially when fine-tuning zone ratios:
602 - Having a lot of offline memory blocks. Even offline memory blocks consume
606 - Memory ballooning without balloon compaction is incompatible with
607 ZONE_MOVABLE. Only some implementations, such as virtio-balloon and
615 - Gigantic pages are unmovable, resulting in user space consuming a
618 - Huge pages are unmovable when an architectures does not support huge
621 - Page tables are unmovable. Excessive swapping, mapping extremely large
627 - In certain DAX configurations the memory map for the device memory will be
630 - KASAN can have a significant memory overhead, for example, consuming 1/8th of
633 - Long-term pinning of pages. Techniques that rely on long-term pinnings
649 Documentation/admin-guide/kernel-parameters.rst for their description.
652 ---------------------------------
657 - Memory blocks with memory holes; this applies to memory blocks present during
659 Hyper-V balloon.
661 - Mixed NUMA nodes and mixed zones within a single memory block prevent memory
664 - Special memory blocks prevented by the system from getting offlined. Examples
669 - Memory blocks overlapping with CMA areas cannot be offlined, this applies to
672 - Concurrent activity that operates on the same physical memory area, such as
675 - Out of memory when dissolving huge pages, especially when HugeTLB Vmemmap
690 (-> BUG), memory offlining will keep retrying until it eventually succeeds.