| /Linux-v6.1/Documentation/translations/zh_CN/mm/ |
| D | numa.rst | 13 何为非统一内存访问(NUMA)？
18 从硬件角度看，NUMA系统是一个由多个组件或装配组成的计算机平台，每个组件可能包含0个或更多的CPU、
23 不会在任何给定的单元上填充。NUMA系统的单元通过某种系统互连连接在一起——例如，交叉开关或点对点
24 链接是NUMA系统互连的常见类型。这两种类型的互连都可以聚合起来，以创建NUMA平台，其中的单元与其
27 对于Linux，感兴趣的NUMA平台主要是所谓的缓存相干NUMA--简称ccNUMA系统系统。在ccNUMA系统中，
33 更高的带宽。 NUMA平台可以在任何给定单元上访问多种远程距离的（其他）单元。
35 平台供应商建立NUMA系统并不只是为了让软件开发人员的生活变得有趣。相反，这种架构是提供可扩展
39 这就自然而然有了Linux软件对NUMA系统的视角:
50 此外，对于某些架构，同样以x86为例，Linux支持对额外节点的仿真。对于NUMA仿真，Linux会将现
51 有的节点或者非NUMA平台的系统内存分割成多个节点。每个模拟的节点将管理底层单元物理内存的一部
[all …]
|
| D | page_migration.rst | 15 页面迁移允许在进程运行时在NUMA系统的节点之间移动页面的物理位置。这意味着进程所看到的虚拟地
27 提供了与其他NUMA功能类似的接口。执行 cat ``/proc/<pid>/numa_maps`` 允许轻松查看进
33 在一个进程中移动单个页面。例如，NUMA分析器可以获得一个显示频繁的节点外访问的日志，并可以使
120 尽管迁移最初的目的是为了减少NUMA的内存访问延迟，但压缩也使用迁移来创建高阶页面。
|
| D | memory-model.rst | 18 小孔隙。那么，在完全不同的地址可能有几个连续的范围。而且，别忘了NUMA，即不
37 最简单的内存模型是FLATMEM。这个模型适用于非NUMA系统的连续或大部分连续的
|
| /Linux-v6.1/Documentation/mm/ |
| D | numa.rst | 6 What is NUMA?
12 From the hardware perspective, a NUMA system is a computer platform that
21 may not be populated on any given cell. The cells of the NUMA system are
23 point-to-point link are common types of NUMA system interconnects. Both of
24 these types of interconnects can be aggregated to create NUMA platforms with
27 For Linux, the NUMA platforms of interest are primarily what is known as Cache
28 Coherent NUMA or ccNUMA systems. With ccNUMA systems, all memory is visible
36 bandwidths than accesses to memory on other, remote cells. NUMA platforms
39 Platform vendors don't build NUMA systems just to make software developers'
46 This leads to the Linux software view of a NUMA system:
[all …]
|
| /Linux-v6.1/Documentation/translations/zh_CN/scheduler/ |
| D | sched-debug.rst | 20 `numa_balancing` 目录用来存放控制非统一内存访问（NUMA）平衡特性的相关文件。
22 scan_period_max_ms, scan_size_mb` 文件控制NUMA缺页的内核采样速率。
28 自动NUMA平衡会扫描任务地址空间，检测页面是否被正确放置，或者数据是否应该被
|
| D | sched-domains.rst | 59 接下来，如果是非统一内存访问（NUMA）系统，SMP调度域的父调度域将管辖整个机器，一个结点的
60 CPU掩码对应一个调度组。亦或，你可以使用多级NUMA；举例来说Opteron处理器，可能仅用一个
61 调度域来覆盖它的一个NUMA层级。
|
| /Linux-v6.1/Documentation/translations/zh_CN/admin-guide/mm/ |
| D | ksm.rst | 85 指定是否可以合并来自不同NUMA节点的页面。当设置为0时，ksm仅合并在物理上位
86 于同一NUMA节点的内存区域中的页面。这降低了访问共享页面的延迟。在有明显的
87 NUMA距离上，具有更多节点的系统可能受益于设置该值为0时的更低延迟。而对于
119 越慢。减慢了这种遍历速度就意味着在交换、压缩、NUMA平衡和页面迁移期间，
|
| /Linux-v6.1/Documentation/powerpc/ |
| D | associativity.rst | 2 NUMA resource associativity
10 characteristic is presented in terms of NUMA node distance within the Linux kernel.
24 Form 0 associativity supports only two NUMA distances (LOCAL and REMOTE).
29 device tree properties are used to determine the NUMA distance between resource groups/domains.
41 Linux kernel uses the domainID at the primary domainID index as the NUMA node id.
42 Linux kernel computes NUMA distance between two domains by recursively comparing
44 level of the resource group, the kernel doubles the NUMA distance between the
49 Form 2 associativity format adds separate device tree properties representing NUMA node distance
71 "ibm,numa-distance-table" property contains a list of one or more numbers representing the NUMA
|
| /Linux-v6.1/Documentation/devicetree/bindings/ |
| D | numa.txt | 2 NUMA binding description.
9 Systems employing a Non Uniform Memory Access (NUMA) architecture contain
11 that comprise what is commonly known as a NUMA node.
12 Processor accesses to memory within the local NUMA node is generally faster
13 than processor accesses to memory outside of the local NUMA node.
14 DT defines interfaces that allow the platform to convey NUMA node
21 For the purpose of identification, each NUMA node is associated with a unique
25 A device node is associated with a NUMA node by the presence of a
110 device nodes for these empty memory nodes. However, the NUMA node IDs and
|
| /Linux-v6.1/Documentation/translations/zh_CN/filesystems/ |
| D | tmpfs.rst | 72 tmpfs具有为所有文件设置NUMA内存分配策略挂载选项(如果启用了CONFIG_NUMA),
94 NUMA内存分配策略有可选标志，可以用于模式结合。在挂载tmpfs时指定这些可选
106 请注意，如果内核不支持NUMA，那么使用mpol选项挂载tmpfs将会失败；nodelist指定不
107 在线的节点也会失败。如果您的系统依赖于此，但内核会运行不带NUMA功能(也许是安全
|
| /Linux-v6.1/Documentation/translations/zh_TW/filesystems/ |
| D | tmpfs.rst | 73 tmpfs具有爲所有文件設置NUMA內存分配策略掛載選項(如果啓用了CONFIG_NUMA),
95 NUMA內存分配策略有可選標誌，可以用於模式結合。在掛載tmpfs時指定這些可選
107 請注意，如果內核不支持NUMA，那麼使用mpol選項掛載tmpfs將會失敗；nodelist指定不
108 在線的節點也會失敗。如果您的系統依賴於此，但內核會運行不帶NUMA功能(也許是安全
|
| /Linux-v6.1/kernel/ |
| D | Kconfig.hz | 12 beneficial for servers and NUMA systems that do not need to have
23 100 Hz is a typical choice for servers, SMP and NUMA systems
32 on SMP and NUMA systems. If you are going to be using NTSC video
40 on SMP and NUMA systems and exactly dividing by both PAL and
|
| /Linux-v6.1/Documentation/ABI/testing/ |
| D | sysfs-kernel-mm-numa | 4 Description: Interface for NUMA
14 characteristics instead of plain NUMA systems where
19 is performed before swap. It may move data to a NUMA
|
| D | ppc-memtrace | 14 you want removed from each NUMA node to this file - it must be
16 from each NUMA node in the kernel mappings and the following
27 from the specific NUMA node.
|
| /Linux-v6.1/drivers/acpi/numa/ |
| D | Kconfig | 3 bool "NUMA support"
4 depends on NUMA
|
| /Linux-v6.1/Documentation/x86/x86_64/ |
| D | fake-numa-for-cpusets.rst | 4 Fake NUMA For CPUSets
13 you can create fake NUMA nodes that represent contiguous chunks of memory and
23 For the purposes of this introduction, we'll assume a very primitive NUMA
65 case (i.e. running the same 'dd' command without assigning it to a fake NUMA
|
| /Linux-v6.1/Documentation/scheduler/ |
| D | sched-debug.rst | 12 `numa_balancing` directory is used to hold files to control NUMA
14 high then the rate the kernel samples for NUMA hinting faults may be
22 Automatic NUMA balancing scans tasks address space and unmaps pages to
|
| /Linux-v6.1/arch/mips/sgi-ip27/ |
| D | Kconfig | 31 NUMA. If you need to understand it, read the source code.
39 nodes in a NUMA cluster. This trades memory for speed.
|
| /Linux-v6.1/tools/testing/memblock/ |
| D | README | 11 within the requested range and/or in specific NUMA node, and many more.
48 the test functions. For example, to simulate enabled NUMA, use:
50 $ make NUMA=1
107 1. Requesting a specific NUMA node via memblock_alloc_node() does not work as
|
| /Linux-v6.1/arch/ia64/ |
| D | Kconfig | 18 select ACPI_NUMA if NUMA
63 select NUMA if !FLATMEM
289 config NUMA config
290 bool "NUMA support"
295 Say Y to compile the kernel to support NUMA (Non-Uniform Memory
303 depends on NUMA
311 depends on NUMA
314 def_bool NUMA
|
| /Linux-v6.1/tools/testing/memblock/scripts/ |
| D | Makefile.include | 5 ifeq ($(NUMA), 1)
|
| /Linux-v6.1/arch/loongarch/ |
| D | Kconfig | 104 select HAVE_SETUP_PER_CPU_AREA if NUMA
385 config NUMA config
386 bool "NUMA Support"
390 Say Y to compile the kernel with NUMA (Non-Uniform Memory Access)
392 than one NUMA node; on single node systems it is generally better
398 depends on NUMA
486 depends on !NUMA
492 for architectures which are either NUMA (Non-Uniform Memory Access)
|
| /Linux-v6.1/arch/sh/mm/ |
| D | Kconfig | 107 config NUMA config
108 bool "Non-Uniform Memory Access (NUMA) Support"
123 depends on NUMA
127 depends on !NUMA
|
| /Linux-v6.1/Documentation/features/sched/numa-balancing/ |
| D | arch-support.txt | 4 # description: arch supports NUMA balancing
|
| /Linux-v6.1/Documentation/translations/zh_CN/core-api/ |
| D | boot-time-mm.rst | 26 第一个（也可能是唯一的）节点或NUMA系统中的某个特定节点。有一些API变体在分
|
