6 Add description of notifier of memory hotplug Oct 11 2007
8 This document is about memory hotplug including how-to-use and current status.
9 Because Memory Hotplug is still under development, contents of this text will
13 1.1 purpose of memory hotplug
14 1.2. Phases of memory hotplug
15 1.3. Unit of Memory online/offline operation
16 2. Kernel Configuration
17 3. sysfs files for memory hotplug
18 4. Physical memory hot-add phase
19 4.1 Hardware(Firmware) Support
20 4.2 Notify memory hot-add event by hand
21 5. Logical Memory hot-add phase
23 5.2. How to online memory
24 6. Logical memory remove
25 6.1 Memory offline and ZONE_MOVABLE
26 6.2. How to offline memory
27 7. Physical memory remove
28 8. Memory hotplug event notifier
31 Note(1): x86_64's has special implementation for memory hotplug.
32 This text does not describe it.
33 Note(2): This text assumes that sysfs is mounted at /sys.
40 1.1 purpose of memory hotplug
42 Memory Hotplug allows users to increase/decrease the amount of memory.
43 Generally, there are two purposes.
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.
50 (A) is required by highly virtualized environments and (B) is required by
51 hardware which supports memory power management.
53 Linux memory hotplug is designed for both purpose.
56 1.2. Phases of memory hotplug
58 There are 2 phases in Memory Hotplug.
59 1) Physical Memory Hotplug phase
60 2) Logical Memory Hotplug phase.
62 The First phase is to communicate hardware/firmware and make/erase
63 environment for hotplugged memory. Basically, this phase is necessary
64 for the purpose (B), but this is good phase for communication between
65 highly virtualized environments too.
67 When memory is hotplugged, the kernel recognizes new memory, makes new memory
68 management tables, and makes sysfs files for new memory's operation.
70 If firmware supports notification of connection of new memory to OS,
71 this phase is triggered automatically. ACPI can notify this event. If not,
72 "probe" operation by system administration is used instead.
75 Logical Memory Hotplug phase is to change memory state into
76 available/unavailable for users. Amount of memory from user's view is
77 changed by this phase. The kernel makes all memory in it as free pages
78 when a memory range is available.
80 In this document, this phase is described as online/offline.
82 Logical Memory Hotplug phase is triggered by write of sysfs file by system
83 administrator. For the hot-add case, it must be executed after Physical Hotplug
85 (However, if you writes udev's hotplug scripts for memory hotplug, these
86 phases can be execute in seamless way.)
89 1.3. Unit of Memory online/offline operation
91 Memory hotplug uses SPARSEMEM memory model. SPARSEMEM divides the whole memory
92 into chunks of the same size. The chunk is called a "section". The size of
93 a section is architecture dependent. For example, power uses 16MiB, ia64 uses
94 1GiB. The unit of online/offline operation is "one section". (see Section 3.)
96 To determine the size of sections, please read this file:
98 /sys/devices/system/memory/block_size_bytes
100 This file shows the size of sections in byte.
102 -----------------------
103 2. Kernel Configuration
104 -----------------------
105 To use memory hotplug feature, kernel must be compiled with following
108 - For all memory hotplug
109 Memory model -> Sparse Memory (CONFIG_SPARSEMEM)
110 Allow for memory hot-add (CONFIG_MEMORY_HOTPLUG)
112 - To enable memory removal, the followings are also necessary
113 Allow for memory hot remove (CONFIG_MEMORY_HOTREMOVE)
114 Page Migration (CONFIG_MIGRATION)
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.
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.
126 --------------------------------
127 4 sysfs files for memory hotplug
128 --------------------------------
129 All sections have their device information in sysfs. Each section is part of
130 a memory block under /sys/devices/system/memory as
132 /sys/devices/system/memory/memoryXXX
133 (XXX is the section id.)
135 Now, XXX is defined as (start_address_of_section / section_size) of the first
136 section 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
138 for the memory block covered by the sysfs directory. It is expected that all
139 memory sections in this range are present and no memory holes exist in the
140 range. Currently there is no way to determine if there is a memory hole, but
141 the existence of one should not affect the hotplug capabilities of the memory
144 For example, assume 1GiB section size. A device for a memory starting at
145 0x100000000 is /sys/device/system/memory/memory4
146 (0x100000000 / 1Gib = 4)
147 This device covers address range [0x100000000 ... 0x140000000)
149 Under each section, you can see 4 or 5 files, the end_phys_index file being
150 a recent addition and not present on older kernels.
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
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
163 at read: contains online/offline state of memory.
164 at write: user can specify "online_kernel",
165 "online_movable", "online", "offline" command
166 which will be performed on al sections in the block.
167 'phys_device' : read-only: designed to show the name of physical memory
168 device. This is not well implemented now.
169 'removable' : read-only: contains an integer value indicating
170 whether the memory block is removable or not
171 removable. A value of 1 indicates that the memory
172 block is removable and a value of 0 indicates that
173 it is not removable. A memory block is removable only if
174 every section in the block is removable.
177 These directories/files appear after physical memory hotplug phase.
179 If CONFIG_NUMA is enabled the memoryXXX/ directories can also be accessed
180 via symbolic links located in the /sys/devices/system/node/node* directories.
183 /sys/devices/system/node/node0/memory9 -> ../../memory/memory9
185 A backlink will also be created:
186 /sys/devices/system/memory/memory9/node0 -> ../../node/node0
188 --------------------------------
189 4. Physical memory hot-add phase
190 --------------------------------
192 4.1 Hardware(Firmware) Support
194 On x86_64/ia64 platform, memory hotplug by ACPI is supported.
196 In general, the firmware (ACPI) which supports memory hotplug defines
197 memory class object of _HID "PNP0C80". When a notify is asserted to PNP0C80,
198 Linux's ACPI handler does hot-add memory to the system and calls a hotplug udev
199 script. This will be done automatically.
201 But scripts for memory hotplug are not contained in generic udev package(now).
202 You may have to write it by yourself or online/offline memory by hand.
203 Please see "How to online memory", "How to offline memory" in this text.
205 If firmware supports NUMA-node hotplug, and defines an object _HID "ACPI0004",
206 "PNP0A05", or "PNP0A06", notification is asserted to it, and ACPI handler
207 calls hotplug code for all of objects which are defined in it.
208 If memory device is found, memory hotplug code will be called.
211 4.2 Notify memory hot-add event by hand
213 On powerpc, the firmware does not notify a memory hotplug event to the kernel.
214 Therefore, "probe" interface is supported to notify the event to the kernel.
215 This interface depends on CONFIG_ARCH_MEMORY_PROBE.
217 CONFIG_ARCH_MEMORY_PROBE is supported on powerpc only. On x86, this config
218 option is disabled by default since ACPI notifies a memory hotplug event to
219 the kernel, which performs its hotplug operation as the result. Please
220 enable this option if you need the "probe" interface for testing purposes
223 Probe interface is located at
224 /sys/devices/system/memory/probe
226 You can tell the physical address of new memory to the kernel by
228 % echo start_address_of_new_memory > /sys/devices/system/memory/probe
230 Then, [start_address_of_new_memory, start_address_of_new_memory + section_size)
231 memory range is hot-added. In this case, hotplug script is not called (in
232 current implementation). You'll have to online memory by yourself.
233 Please see "How to online memory" in this text.
237 ------------------------------
238 5. Logical Memory hot-add phase
239 ------------------------------
243 To see (online/offline) state of memory section, read 'state' file.
245 % cat /sys/device/system/memory/memoryXXX/state
248 If the memory section is online, you'll read "online".
249 If the memory section is offline, you'll read "offline".
252 5.2. How to online memory
254 Even if the memory is hot-added, it is not at ready-to-use state.
255 For using newly added memory, you have to "online" the memory section.
257 For onlining, you have to write "online" to the section's state file as:
259 % echo online > /sys/devices/system/memory/memoryXXX/state
261 This onlining will not change the ZONE type of the target memory section,
262 If the memory section is in ZONE_NORMAL, you can change it to ZONE_MOVABLE:
264 % echo online_movable > /sys/devices/system/memory/memoryXXX/state
265 (NOTE: current limit: this memory section must be adjacent to ZONE_MOVABLE)
267 And if the memory section is in ZONE_MOVABLE, you can change it to ZONE_NORMAL:
269 % echo online_kernel > /sys/devices/system/memory/memoryXXX/state
270 (NOTE: current limit: this memory section must be adjacent to ZONE_NORMAL)
272 After this, section memoryXXX's state will be 'online' and the amount of
273 available memory will be increased.
275 Currently, newly added memory is added as ZONE_NORMAL (for powerpc, ZONE_DMA).
276 This may be changed in future.
280 ------------------------
281 6. Logical memory remove
282 ------------------------
284 6.1 Memory offline and ZONE_MOVABLE
286 Memory offlining is more complicated than memory online. Because memory offline
287 has to make the whole memory section be unused, memory offline can fail if
288 the section includes memory which cannot be freed.
290 In general, memory offline can use 2 techniques.
292 (1) reclaim and free all memory in the section.
293 (2) migrate all pages in the section.
295 In the current implementation, Linux's memory offline uses method (2), freeing
296 all pages in the section by page migration. But not all pages are
297 migratable. Under current Linux, migratable pages are anonymous pages and
298 page caches. For offlining a section by migration, the kernel has to guarantee
299 that the section contains only migratable pages.
301 Now, a boot option for making a section which consists of migratable pages is
302 supported. By specifying "kernelcore=" or "movablecore=" boot option, you can
303 create ZONE_MOVABLE...a zone which is just used for movable pages.
304 (See also Documentation/kernel-parameters.txt)
306 Assume the system has "TOTAL" amount of memory at boot time, this boot option
307 creates ZONE_MOVABLE as following.
309 1) When kernelcore=YYYY boot option is used,
310 Size of memory not for movable pages (not for offline) is YYYY.
311 Size of memory for movable pages (for offline) is TOTAL-YYYY.
313 2) When movablecore=ZZZZ boot option is used,
314 Size of memory not for movable pages (not for offline) is TOTAL - ZZZZ.
315 Size of memory for movable pages (for offline) is ZZZZ.
318 Note) Unfortunately, there is no information to show which section belongs
319 to ZONE_MOVABLE. This is TBD.
322 6.2. How to offline memory
324 You can offline a section by using the same sysfs interface that was used in
327 % echo offline > /sys/devices/system/memory/memoryXXX/state
329 If offline succeeds, the state of the memory section is changed to be "offline".
330 If it fails, some error core (like -EBUSY) will be returned by the kernel.
331 Even if a section does not belong to ZONE_MOVABLE, you can try to offline it.
332 If it doesn't contain 'unmovable' memory, you'll get success.
334 A section under ZONE_MOVABLE is considered to be able to be offlined easily.
335 But under some busy state, it may return -EBUSY. Even if a memory section
336 cannot be offlined due to -EBUSY, you can retry offlining it and may be able to
338 (For example, a page is referred to by some kernel internal call and released
342 Memory hotplug's design direction is to make the possibility of memory offlining
343 higher and to guarantee unplugging memory under any situation. But it needs
344 more work. Returning -EBUSY under some situation may be good because the user
345 can decide to retry more or not by himself. Currently, memory offlining code
346 does some amount of retry with 120 seconds timeout.
348 -------------------------
349 7. Physical memory remove
350 -------------------------
351 Need more implementation yet....
352 - Notification completion of remove works by OS to firmware.
353 - Guard from remove if not yet.
355 --------------------------------
356 8. Memory hotplug event notifier
357 --------------------------------
358 Memory hotplug has event notifier. There are 6 types of notification.
361 Generated before new memory becomes available in order to be able to
362 prepare subsystems to handle memory. The page allocator is still unable
363 to allocate from the new memory.
366 Generated if MEMORY_GOING_ONLINE fails.
369 Generated when memory has successfully brought online. The callback may
370 allocate pages from the new memory.
373 Generated to begin the process of offlining memory. Allocations are no
374 longer possible from the memory but some of the memory to be offlined
375 is still in use. The callback can be used to free memory known to a
376 subsystem from the indicated memory section.
378 MEMORY_CANCEL_OFFLINE
379 Generated if MEMORY_GOING_OFFLINE fails. Memory is available again from
380 the section that we attempted to offline.
383 Generated after offlining memory is complete.
385 A callback routine can be registered by
386 hotplug_memory_notifier(callback_func, priority)
388 The second argument of callback function (action) is event types of above.
389 The third argument is passed by pointer of struct memory_notify.
391 struct memory_notify {
392 unsigned long start_pfn;
393 unsigned long nr_pages;
394 int status_change_nid_normal;
395 int status_change_nid_high;
396 int status_change_nid;
399 start_pfn is start_pfn of online/offline memory.
400 nr_pages is # of pages of online/offline memory.
401 status_change_nid_normal is set node id when N_NORMAL_MEMORY of nodemask
402 is (will be) set/clear, if this is -1, then nodemask status is not changed.
403 status_change_nid_high is set node id when N_HIGH_MEMORY of nodemask
404 is (will be) set/clear, if this is -1, then nodemask status is not changed.
405 status_change_nid is set node id when N_MEMORY of nodemask is (will be)
406 set/clear. It means a new(memoryless) node gets new memory by online and a
407 node loses all memory. If this is -1, then nodemask status is not changed.
408 If status_changed_nid* >= 0, callback should create/discard structures for the
414 - allowing memory hot-add to ZONE_MOVABLE. maybe we need some switch like
415 sysctl or new control file.
416 - showing memory section and physical device relationship.
417 - showing memory section is under ZONE_MOVABLE or not
418 - test and make it better memory offlining.
419 - support HugeTLB page migration and offlining.
420 - memmap removing at memory offline.
421 - physical remove memory.