linux/Documentation/memory-hotplug.txt
<<
>>
Prefs
   1==============
   2Memory Hotplug
   3==============
   4
   5Created:                                        Jul 28 2007
   6Add description of notifier of memory hotplug   Oct 11 2007
   7
   8This document is about memory hotplug including how-to-use and current status.
   9Because Memory Hotplug is still under development, contents of this text will
  10be changed often.
  11
  121. Introduction
  13  1.1 purpose of memory hotplug
  14  1.2. Phases of memory hotplug
  15  1.3. Unit of Memory online/offline operation
  162. Kernel Configuration
  173. sysfs files for memory hotplug
  184. Physical memory hot-add phase
  19  4.1 Hardware(Firmware) Support
  20  4.2 Notify memory hot-add event by hand
  215. Logical Memory hot-add phase
  22  5.1. State of memory
  23  5.2. How to online memory
  246. Logical memory remove
  25  6.1 Memory offline and ZONE_MOVABLE
  26  6.2. How to offline memory
  277. Physical memory remove
  288. Memory hotplug event notifier
  299. Future Work List
  30
  31Note(1): x86_64's has special implementation for memory hotplug.
  32         This text does not describe it.
  33Note(2): This text assumes that sysfs is mounted at /sys.
  34
  35
  36---------------
  371. Introduction
  38---------------
  39
  401.1 purpose of memory hotplug
  41------------
  42Memory Hotplug allows users to increase/decrease the amount of memory.
  43Generally, there are two purposes.
  44
  45(A) For changing the amount of memory.
  46    This is to allow a feature like capacity on demand.
  47(B) For installing/removing DIMMs or NUMA-nodes physically.
  48    This is to exchange DIMMs/NUMA-nodes, reduce power consumption, etc.
  49
  50(A) is required by highly virtualized environments and (B) is required by
  51hardware which supports memory power management.
  52
  53Linux memory hotplug is designed for both purpose.
  54
  55
  561.2. Phases of memory hotplug
  57---------------
  58There are 2 phases in Memory Hotplug.
  59  1) Physical Memory Hotplug phase
  60  2) Logical Memory Hotplug phase.
  61
  62The First phase is to communicate hardware/firmware and make/erase
  63environment for hotplugged memory. Basically, this phase is necessary
  64for the purpose (B), but this is good phase for communication between
  65highly virtualized environments too.
  66
  67When memory is hotplugged, the kernel recognizes new memory, makes new memory
  68management tables, and makes sysfs files for new memory's operation.
  69
  70If firmware supports notification of connection of new memory to OS,
  71this phase is triggered automatically. ACPI can notify this event. If not,
  72"probe" operation by system administration is used instead.
  73(see Section 4.).
  74
  75Logical Memory Hotplug phase is to change memory state into
  76available/unavailable for users. Amount of memory from user's view is
  77changed by this phase. The kernel makes all memory in it as free pages
  78when a memory range is available.
  79
  80In this document, this phase is described as online/offline.
  81
  82Logical Memory Hotplug phase is triggered by write of sysfs file by system
  83administrator. For the hot-add case, it must be executed after Physical Hotplug
  84phase by hand.
  85(However, if you writes udev's hotplug scripts for memory hotplug, these
  86 phases can be execute in seamless way.)
  87
  88
  891.3. Unit of Memory online/offline operation
  90------------
  91Memory hotplug uses SPARSEMEM memory model. SPARSEMEM divides the whole memory
  92into chunks of the same size. The chunk is called a "section". The size of
  93a section is architecture dependent. For example, power uses 16MiB, ia64 uses
  941GiB. The unit of online/offline operation is "one section". (see Section 3.)
  95
  96To determine the size of sections, please read this file:
  97
  98/sys/devices/system/memory/block_size_bytes
  99
 100This file shows the size of sections in byte.
 101
 102-----------------------
 1032. Kernel Configuration
 104-----------------------
 105To use memory hotplug feature, kernel must be compiled with following
 106config options.
 107
 108- For all memory hotplug
 109    Memory model -> Sparse Memory  (CONFIG_SPARSEMEM)
 110    Allow for memory hot-add       (CONFIG_MEMORY_HOTPLUG)
 111
 112- To enable memory removal, the followings are also necessary
 113    Allow for memory hot remove    (CONFIG_MEMORY_HOTREMOVE)
 114    Page Migration                 (CONFIG_MIGRATION)
 115
 116- For ACPI memory hotplug, the followings are also necessary
 117    Memory hotplug (under ACPI Support menu) (CONFIG_ACPI_HOTPLUG_MEMORY)
 118    This option can be kernel module.
 119
 120- As a related configuration, if your box has a feature of NUMA-node hotplug
 121  via ACPI, then this option is necessary too.
 122    ACPI0004,PNP0A05 and PNP0A06 Container Driver (under ACPI Support menu)
 123    (CONFIG_ACPI_CONTAINER).
 124    This option can be kernel module too.
 125
 126--------------------------------
 1274 sysfs files for memory hotplug
 128--------------------------------
 129All sections have their device information in sysfs.  Each section is part of
 130a memory block under /sys/devices/system/memory as
 131
 132/sys/devices/system/memory/memoryXXX
 133(XXX is the section id.)
 134
 135Now, XXX is defined as (start_address_of_section / section_size) of the first
 136section contained in the memory block.  The files 'phys_index' and
 137'end_phys_index' under each directory report the beginning and end section id's
 138for the memory block covered by the sysfs directory.  It is expected that all
 139memory sections in this range are present and no memory holes exist in the
 140range. Currently there is no way to determine if there is a memory hole, but
 141the existence of one should not affect the hotplug capabilities of the memory
 142block.
 143
 144For example, assume 1GiB section size. A device for a memory starting at
 1450x100000000 is /sys/device/system/memory/memory4
 146(0x100000000 / 1Gib = 4)
 147This device covers address range [0x100000000 ... 0x140000000)
 148
 149Under each section, you can see 4 or 5 files, the end_phys_index file being
 150a recent addition and not present on older kernels.
 151
 152/sys/devices/system/memory/memoryXXX/start_phys_index
 153/sys/devices/system/memory/memoryXXX/end_phys_index
 154/sys/devices/system/memory/memoryXXX/phys_device
 155/sys/devices/system/memory/memoryXXX/state
 156/sys/devices/system/memory/memoryXXX/removable
 157
 158'phys_index'      : read-only and contains section id of the first section
 159                    in the memory block, same as XXX.
 160'end_phys_index'  : read-only and contains section id of the last section
 161                    in the memory block.
 162'state'           : read-write
 163                    at read:  contains online/offline state of memory.
 164                    at write: user can specify "online", "offline" command
 165                    which will be performed on al sections in the block.
 166'phys_device'     : read-only: designed to show the name of physical memory
 167                    device.  This is not well implemented now.
 168'removable'       : read-only: contains an integer value indicating
 169                    whether the memory block is removable or not
 170                    removable.  A value of 1 indicates that the memory
 171                    block is removable and a value of 0 indicates that
 172                    it is not removable. A memory block is removable only if
 173                    every section in the block is removable.
 174
 175NOTE:
 176  These directories/files appear after physical memory hotplug phase.
 177
 178If CONFIG_NUMA is enabled the memoryXXX/ directories can also be accessed
 179via symbolic links located in the /sys/devices/system/node/node* directories.
 180
 181For example:
 182/sys/devices/system/node/node0/memory9 -> ../../memory/memory9
 183
 184A backlink will also be created:
 185/sys/devices/system/memory/memory9/node0 -> ../../node/node0
 186
 187--------------------------------
 1884. Physical memory hot-add phase
 189--------------------------------
 190
 1914.1 Hardware(Firmware) Support
 192------------
 193On x86_64/ia64 platform, memory hotplug by ACPI is supported.
 194
 195In general, the firmware (ACPI) which supports memory hotplug defines
 196memory class object of _HID "PNP0C80". When a notify is asserted to PNP0C80,
 197Linux's ACPI handler does hot-add memory to the system and calls a hotplug udev
 198script. This will be done automatically.
 199
 200But scripts for memory hotplug are not contained in generic udev package(now).
 201You may have to write it by yourself or online/offline memory by hand.
 202Please see "How to online memory", "How to offline memory" in this text.
 203
 204If firmware supports NUMA-node hotplug, and defines an object _HID "ACPI0004",
 205"PNP0A05", or "PNP0A06", notification is asserted to it, and ACPI handler
 206calls hotplug code for all of objects which are defined in it.
 207If memory device is found, memory hotplug code will be called.
 208
 209
 2104.2 Notify memory hot-add event by hand
 211------------
 212In some environments, especially virtualized environment, firmware will not
 213notify memory hotplug event to the kernel. For such environment, "probe"
 214interface is supported. This interface depends on CONFIG_ARCH_MEMORY_PROBE.
 215
 216Now, CONFIG_ARCH_MEMORY_PROBE is supported only by powerpc but it does not
 217contain highly architecture codes. Please add config if you need "probe"
 218interface.
 219
 220Probe interface is located at
 221/sys/devices/system/memory/probe
 222
 223You can tell the physical address of new memory to the kernel by
 224
 225% echo start_address_of_new_memory > /sys/devices/system/memory/probe
 226
 227Then, [start_address_of_new_memory, start_address_of_new_memory + section_size)
 228memory range is hot-added. In this case, hotplug script is not called (in
 229current implementation). You'll have to online memory by yourself.
 230Please see "How to online memory" in this text.
 231
 232
 233
 234------------------------------
 2355. Logical Memory hot-add phase
 236------------------------------
 237
 2385.1. State of memory
 239------------
 240To see (online/offline) state of memory section, read 'state' file.
 241
 242% cat /sys/device/system/memory/memoryXXX/state
 243
 244
 245If the memory section is online, you'll read "online".
 246If the memory section is offline, you'll read "offline".
 247
 248
 2495.2. How to online memory
 250------------
 251Even if the memory is hot-added, it is not at ready-to-use state.
 252For using newly added memory, you have to "online" the memory section.
 253
 254For onlining, you have to write "online" to the section's state file as:
 255
 256% echo online > /sys/devices/system/memory/memoryXXX/state
 257
 258After this, section memoryXXX's state will be 'online' and the amount of
 259available memory will be increased.
 260
 261Currently, newly added memory is added as ZONE_NORMAL (for powerpc, ZONE_DMA).
 262This may be changed in future.
 263
 264
 265
 266------------------------
 2676. Logical memory remove
 268------------------------
 269
 2706.1 Memory offline and ZONE_MOVABLE
 271------------
 272Memory offlining is more complicated than memory online. Because memory offline
 273has to make the whole memory section be unused, memory offline can fail if
 274the section includes memory which cannot be freed.
 275
 276In general, memory offline can use 2 techniques.
 277
 278(1) reclaim and free all memory in the section.
 279(2) migrate all pages in the section.
 280
 281In the current implementation, Linux's memory offline uses method (2), freeing
 282all  pages in the section by page migration. But not all pages are
 283migratable. Under current Linux, migratable pages are anonymous pages and
 284page caches. For offlining a section by migration, the kernel has to guarantee
 285that the section contains only migratable pages.
 286
 287Now, a boot option for making a section which consists of migratable pages is
 288supported. By specifying "kernelcore=" or "movablecore=" boot option, you can
 289create ZONE_MOVABLE...a zone which is just used for movable pages.
 290(See also Documentation/kernel-parameters.txt)
 291
 292Assume the system has "TOTAL" amount of memory at boot time, this boot option
 293creates ZONE_MOVABLE as following.
 294
 2951) When kernelcore=YYYY boot option is used,
 296  Size of memory not for movable pages (not for offline) is YYYY.
 297  Size of memory for movable pages (for offline) is TOTAL-YYYY.
 298
 2992) When movablecore=ZZZZ boot option is used,
 300  Size of memory not for movable pages (not for offline) is TOTAL - ZZZZ.
 301  Size of memory for movable pages (for offline) is ZZZZ.
 302
 303
 304Note) Unfortunately, there is no information to show which section belongs
 305to ZONE_MOVABLE. This is TBD.
 306
 307
 3086.2. How to offline memory
 309------------
 310You can offline a section by using the same sysfs interface that was used in
 311memory onlining.
 312
 313% echo offline > /sys/devices/system/memory/memoryXXX/state
 314
 315If offline succeeds, the state of the memory section is changed to be "offline".
 316If it fails, some error core (like -EBUSY) will be returned by the kernel.
 317Even if a section does not belong to ZONE_MOVABLE, you can try to offline it.
 318If it doesn't contain 'unmovable' memory, you'll get success.
 319
 320A section under ZONE_MOVABLE is considered to be able to be offlined easily.
 321But under some busy state, it may return -EBUSY. Even if a memory section
 322cannot be offlined due to -EBUSY, you can retry offlining it and may be able to
 323offline it (or not).
 324(For example, a page is referred to by some kernel internal call and released
 325 soon.)
 326
 327Consideration:
 328Memory hotplug's design direction is to make the possibility of memory offlining
 329higher and to guarantee unplugging memory under any situation. But it needs
 330more work. Returning -EBUSY under some situation may be good because the user
 331can decide to retry more or not by himself. Currently, memory offlining code
 332does some amount of retry with 120 seconds timeout.
 333
 334-------------------------
 3357. Physical memory remove
 336-------------------------
 337Need more implementation yet....
 338 - Notification completion of remove works by OS to firmware.
 339 - Guard from remove if not yet.
 340
 341--------------------------------
 3428. Memory hotplug event notifier
 343--------------------------------
 344Memory hotplug has event notifer. There are 6 types of notification.
 345
 346MEMORY_GOING_ONLINE
 347  Generated before new memory becomes available in order to be able to
 348  prepare subsystems to handle memory. The page allocator is still unable
 349  to allocate from the new memory.
 350
 351MEMORY_CANCEL_ONLINE
 352  Generated if MEMORY_GOING_ONLINE fails.
 353
 354MEMORY_ONLINE
 355  Generated when memory has successfully brought online. The callback may
 356  allocate pages from the new memory.
 357
 358MEMORY_GOING_OFFLINE
 359  Generated to begin the process of offlining memory. Allocations are no
 360  longer possible from the memory but some of the memory to be offlined
 361  is still in use. The callback can be used to free memory known to a
 362  subsystem from the indicated memory section.
 363
 364MEMORY_CANCEL_OFFLINE
 365  Generated if MEMORY_GOING_OFFLINE fails. Memory is available again from
 366  the section that we attempted to offline.
 367
 368MEMORY_OFFLINE
 369  Generated after offlining memory is complete.
 370
 371A callback routine can be registered by
 372  hotplug_memory_notifier(callback_func, priority)
 373
 374The second argument of callback function (action) is event types of above.
 375The third argument is passed by pointer of struct memory_notify.
 376
 377struct memory_notify {
 378       unsigned long start_pfn;
 379       unsigned long nr_pages;
 380       int status_change_nid;
 381}
 382
 383start_pfn is start_pfn of online/offline memory.
 384nr_pages is # of pages of online/offline memory.
 385status_change_nid is set node id when N_HIGH_MEMORY of nodemask is (will be)
 386set/clear. It means a new(memoryless) node gets new memory by online and a
 387node loses all memory. If this is -1, then nodemask status is not changed.
 388If status_changed_nid >= 0, callback should create/discard structures for the
 389node if necessary.
 390
 391--------------
 3929. Future Work
 393--------------
 394  - allowing memory hot-add to ZONE_MOVABLE. maybe we need some switch like
 395    sysctl or new control file.
 396  - showing memory section and physical device relationship.
 397  - showing memory section is under ZONE_MOVABLE or not
 398  - test and make it better memory offlining.
 399  - support HugeTLB page migration and offlining.
 400  - memmap removing at memory offline.
 401  - physical remove memory.
 402
 403