Lines Matching +full:memory +full:- +full:to +full:- +full:memory
2 Memory Resource Controller
8 here but make sure to check the current code if you need a deeper
12 The Memory Resource Controller has generically been referred to as the
13 memory controller in this document. Do not confuse memory controller
14 used here with the memory controller that is used in hardware.
17 When we mention a cgroup (cgroupfs's directory) with memory controller,
18 we call it "memory cgroup". When you see git-log and source code, you'll
19 see patch's title and function names tend to use "memcg".
22 Benefits and Purpose of the memory controller
25 The memory controller isolates the memory behaviour of a group of tasks
27 uses of the memory controller. The memory controller can be used to
30 Memory-hungry applications can be isolated and limited to a smaller
31 amount of memory.
32 b. Create a cgroup with a limited amount of memory; this can be used
33 as a good alternative to booting with mem=XXXX.
34 c. Virtualization solutions can control the amount of memory they want
35 to assign to a virtual machine instance.
36 d. A CD/DVD burner could control the amount of memory used by the
37 rest of the system to ensure that burning does not fail due to lack
38 of available memory.
40 for fun (to learn and hack on the VM subsystem).
42 Current Status: linux-2.6.34-mmotm(development version of 2010/April)
46 - accounting anonymous pages, file caches, swap caches usage and limiting them.
47 - pages are linked to per-memcg LRU exclusively, and there is no global LRU.
48 - optionally, memory+swap usage can be accounted and limited.
49 - hierarchical accounting
50 - soft limit
51 - moving (recharging) account at moving a task is selectable.
52 - usage threshold notifier
53 - memory pressure notifier
54 - oom-killer disable knob and oom-notifier
55 - Root cgroup has no limit controls.
57 Kernel memory support is a work in progress, and the current version provides
59 <cgroup-v1-memory-kernel-extension>`)
69 memory.usage_in_bytes show current usage for memory
71 memory.memsw.usage_in_bytes show current usage for memory+Swap
73 memory.limit_in_bytes set/show limit of memory usage
74 memory.memsw.limit_in_bytes set/show limit of memory+Swap usage
75 memory.failcnt show the number of memory usage hits limits
76 memory.memsw.failcnt show the number of memory+Swap hits limits
77 memory.max_usage_in_bytes show max memory usage recorded
78 memory.memsw.max_usage_in_bytes show max memory+Swap usage recorded
79 memory.soft_limit_in_bytes set/show soft limit of memory usage
81 memory.stat show various statistics
82 memory.use_hierarchy set/show hierarchical account enabled
85 memory.force_empty trigger forced page reclaim
86 memory.pressure_level set memory pressure notifications
87 memory.swappiness set/show swappiness parameter of vmscan
89 memory.move_charge_at_immigrate set/show controls of moving charges
92 memory.oom_control set/show oom controls.
93 memory.numa_stat show the number of memory usage per numa
95 memory.kmem.limit_in_bytes Deprecated knob to set and read the kernel
96 memory hard limit. Kernel hard limit is not
97 supported since 5.16. Writing any value to
100 Kernel memory is still charged and reported
101 by memory.kmem.usage_in_bytes.
102 memory.kmem.usage_in_bytes show current kernel memory allocation
103 memory.kmem.failcnt show the number of kernel memory usage
105 memory.kmem.max_usage_in_bytes show max kernel memory usage recorded
107 memory.kmem.tcp.limit_in_bytes set/show hard limit for tcp buf memory
108 memory.kmem.tcp.usage_in_bytes show current tcp buf memory allocation
109 memory.kmem.tcp.failcnt show the number of tcp buf memory usage
111 memory.kmem.tcp.max_usage_in_bytes show max tcp buf memory usage recorded
117 The memory controller has a long history. A request for comments for the memory
119 there were several implementations for memory control. The goal of the
120 RFC was to build consensus and agreement for the minimal features required
121 for memory control. The first RSS controller was posted by Balbir Singh [2]_
125 raised to allow user space handling of OOM. The current memory controller is
129 2. Memory Control
132 Memory is a unique resource in the sense that it is present in a limited
135 memory, the same physical memory needs to be reused to accomplish the task.
137 The memory controller implementation has been divided into phases. These
140 1. Memory controller
142 3. Kernel user memory accounting and slab control
145 The memory controller is the first controller developed.
148 -----------
151 page_counter tracks the current memory usage and limit of the group of
152 processes associated with the controller. Each cgroup has a memory controller
156 ---------------
158 .. code-block::
161 +--------------------+
164 +--------------------+
167 +---------------+ | +---------------+
170 +---------------+ | +---------------+
172 + --------------+
174 +---------------+ +------+--------+
175 | page +----------> page_cgroup|
177 +---------------+ +---------------+
184 2. Each mm_struct knows about which cgroup it belongs to
185 3. Each page has a pointer to the page_cgroup, which in turn knows the
186 cgroup it belongs to
188 The accounting is done as follows: mem_cgroup_charge_common() is invoked to
192 If everything goes well, a page meta-data-structure called page_cgroup is
194 (*) page_cgroup structure is allocated at boot/memory-hotplug time.
197 ------------------------
212 A swapped-in page is accounted after adding into swapcache.
214 Note: The kernel does swapin-readahead and reads multiple swaps at once.
220 Note: we just account pages-on-LRU because our purpose is to control amount
221 of used pages; not-on-LRU pages tend to be out-of-control from VM view.
224 --------------------------
230 the cgroup that brought it in -- this will happen on memory pressure).
232 But see :ref:`section 8.2 <cgroup-v1-memory-movable-charges>` when moving a
233 task to another cgroup, its pages may be recharged to the new cgroup, if
237 --------------------------------------
239 Swap usage is always recorded for each of cgroup. Swap Extension allows you to
244 - memory.memsw.usage_in_bytes.
245 - memory.memsw.limit_in_bytes.
247 memsw means memory+swap. Usage of memory+swap is limited by
250 Example: Assume a system with 4G of swap. A task which allocates 6G of memory
251 (by mistake) under 2G memory limitation will use all swap.
256 2.4.1 why 'memory+swap' rather than swap
259 The global LRU(kswapd) can swap out arbitrary pages. Swap-out means
260 to move account from memory to swap...there is no change in usage of
261 memory+swap. In other words, when we want to limit the usage of swap without
262 affecting global LRU, memory+swap limit is better than just limiting swap from
265 2.4.2. What happens when a cgroup hits memory.memsw.limit_in_bytes
268 When a cgroup hits memory.memsw.limit_in_bytes, it's useless to do swap-out
269 in this cgroup. Then, swap-out will not be done by cgroup routine and file
270 caches are dropped. But as mentioned above, global LRU can do swapout memory
271 from it for sanity of the system's memory management state. You can't forbid
275 -----------
279 to reclaim memory from the cgroup so as to make space for the new
281 an OOM routine is invoked to select and kill the bulkiest task in the
282 cgroup. (See :ref:`10. OOM Control <cgroup-v1-memory-oom-control>` below.)
285 pages that are selected for reclaiming come from the per-cgroup LRU
293 When panic_on_oom is set to "2", the whole system will panic.
296 (See :ref:`oom_control <cgroup-v1-memory-oom-control>` section)
299 -----------
303 Page lock (PG_locked bit of page->flags)
304 mm->page_table_lock or split pte_lock
305 folio_memcg_lock (memcg->move_lock)
306 mapping->i_pages lock
307 lruvec->lru_lock.
309 Per-node-per-memcgroup LRU (cgroup's private LRU) is guarded by
310 lruvec->lru_lock; PG_lru bit of page->flags is cleared before
311 isolating a page from its LRU under lruvec->lru_lock.
313 .. _cgroup-v1-memory-kernel-extension:
315 2.7 Kernel Memory Extension
316 -----------------------------------------------
318 With the Kernel memory extension, the Memory Controller is able to limit
319 the amount of kernel memory used by the system. Kernel memory is fundamentally
320 different than user memory, since it can't be swapped out, which makes it
321 possible to DoS the system by consuming too much of this precious resource.
323 Kernel memory accounting is enabled for all memory cgroups by default. But
324 it can be disabled system-wide by passing cgroup.memory=nokmem to the kernel
325 at boot time. In this case, kernel memory will not be accounted at all.
327 Kernel memory limits are not imposed for the root cgroup. Usage for the root
328 cgroup may or may not be accounted. The memory used is accumulated into
329 memory.kmem.usage_in_bytes, or in a separate counter when it makes sense.
335 Currently no soft limit is implemented for kernel memory. It is future work
336 to trigger slab reclaim when those limits are reached.
338 2.7.1 Current Kernel Memory resources accounted
339 -----------------------------------------------
343 kernel memory, we prevent new processes from being created when the kernel
344 memory usage is too high.
351 belong to the same memcg. This only fails to hold when a task is migrated to a
354 sockets memory pressure:
355 some sockets protocols have memory pressure
356 thresholds. The Memory Controller allows them to be controlled individually
359 tcp memory pressure:
360 sockets memory pressure for the tcp protocol.
363 ----------------------
365 Because the "kmem" counter is fed to the main user counter, kernel memory can
366 never be limited completely independently of user memory. Say "U" is the user
372 accounting. Kernel memory is completely ignored.
375 Kernel memory is a subset of the user memory. This setup is useful in
376 deployments where the total amount of memory per-cgroup is overcommitted.
377 Overcommitting kernel memory limits is definitely not recommended, since the
378 box can still run out of non-reclaimable memory.
380 never greater than the total memory, and freely set U at the cost of his
384 In the current implementation, memory reclaim will NOT be triggered for
389 Since kmem charges will also be fed to the user counter and reclaim will be
390 triggered for the cgroup for both kinds of memory. This setup gives the
391 admin a unified view of memory, and it is also useful for people who just
392 want to track kernel memory usage.
397 To use the user interface:
401 <cgroups-why-needed>` for the background information)::
403 # mount -t tmpfs none /sys/fs/cgroup
404 # mkdir /sys/fs/cgroup/memory
405 # mount -t cgroup none /sys/fs/cgroup/memory -o memory
409 # mkdir /sys/fs/cgroup/memory/0
410 # echo $$ > /sys/fs/cgroup/memory/0/tasks
412 4. Since now we're in the 0 cgroup, we can alter the memory limit::
414 # echo 4M > /sys/fs/cgroup/memory/0/memory.limit_in_bytes
418 # cat /sys/fs/cgroup/memory/0/memory.limit_in_bytes
422 We can use a suffix (k, K, m, M, g or G) to indicate values in kilo,
427 We can write "-1" to reset the ``*.limit_in_bytes(unlimited)``.
435 # cat /sys/fs/cgroup/memory/0/memory.usage_in_bytes
438 A successful write to this file does not guarantee a successful setting of
439 this limit to the value written into the file. This can be due to a
440 number of factors, such as rounding up to page boundaries or the total
441 availability of memory on the system. The user is required to re-read
442 this file after a write to guarantee the value committed by the kernel::
444 # echo 1 > memory.limit_in_bytes
445 # cat memory.limit_in_bytes
448 The memory.failcnt field gives the number of times that the cgroup limit was
451 The memory.stat file gives accounting information. Now, the number of
459 Performance test is also important. To see pure memory controller's overhead,
463 Page-fault scalability is also important. At measuring parallel
464 page fault test, multi-process test may be better than multi-thread
468 Trying usual test under memory controller is always helpful.
470 .. _cgroup-v1-memory-test-troubleshoot:
473 -------------------
478 1. The cgroup limit is too low (just too low to do anything useful)
479 2. The user is using anonymous memory and swap is turned off or too low
484 To know what happens, disabling OOM_Kill as per :ref:`"10. OOM Control"
485 <cgroup-v1-memory-oom-control>` (below) and seeing what happens will be
488 .. _cgroup-v1-memory-test-task-migration:
491 ------------------
493 When a task migrates from one cgroup to another, its charge is not
495 remain charged to it, the charge is dropped when the page is freed or
499 See :ref:`8. "Move charges at task migration" <cgroup-v1-memory-move-charges>`
502 ---------------------
505 <cgroup-v1-memory-test-troubleshoot>` and :ref:`4.2
506 <cgroup-v1-memory-test-task-migration>`, a cgroup might have some charge
510 We move the stats to parent, and no change on the charge except uncharging
521 ---------------
522 memory.force_empty interface is provided to make cgroup's memory usage empty.
523 When writing anything to this::
525 # echo 0 > memory.force_empty
530 Though rmdir() offlines memcg, but the memcg may still stay there due to
531 charged file caches. Some out-of-use page caches may keep charged until
532 memory pressure happens. If you want to avoid that, force_empty will be useful.
535 -------------
537 memory.stat file includes following statistics:
539 * per-memory cgroup local status
542 cache # of bytes of page cache memory.
543 rss # of bytes of anonymous and swap cache memory (includes
547 pgpgin # of charging events to the memory cgroup. The charging
549 anon page(RSS) or cache page(Page Cache) to the cgroup.
550 pgpgout # of uncharging events to the memory cgroup. The uncharging
554 dirty # of bytes that are waiting to get written back to the disk.
555 writeback # of bytes of file/anon cache that are queued for syncing to
557 inactive_anon # of bytes of anonymous and swap cache memory on inactive
559 active_anon # of bytes of anonymous and swap cache memory on active
561 inactive_file # of bytes of file-backed memory and MADV_FREE anonymous
562 memory (LazyFree pages) on inactive LRU list.
563 active_file # of bytes of file-backed memory on active LRU list.
564 unevictable # of bytes of memory that cannot be reclaimed (mlocked etc).
567 * status considering hierarchy (see memory.use_hierarchy settings):
570 hierarchical_memory_limit # of bytes of memory limit with regard to
572 under which the memory cgroup is
573 hierarchical_memsw_limit # of bytes of memory+swap limit with regard to
574 hierarchy under which memory cgroup is.
577 addition to the cgroup's own value includes the
593 recent_scanned means recent # of scans to LRU.
597 Only anonymous and swap cache memory is listed as part of 'rss' stat.
599 amount of physical memory used by the cgroup.
604 mapped_file is accounted only when the memory cgroup is owner of page
608 --------------
611 in the root cgroup corresponds to the global swappiness setting.
615 there is a swap storage available. This might lead to memcg OOM killer
616 if there are no file pages to reclaim.
619 -----------
621 A memory cgroup provides memory.failcnt and memory.memsw.failcnt files.
623 hit its limit. When a memory cgroup hits a limit, failcnt increases and
624 memory under it will be reclaimed.
626 You can reset failcnt by writing 0 to failcnt file::
628 # echo 0 > .../memory.failcnt
631 ------------------
633 For efficiency, as other kernel components, memory cgroup uses some optimization
634 to avoid unnecessary cacheline false sharing. usage_in_bytes is affected by the
635 method and doesn't show 'exact' value of memory (and swap) usage, it's a fuzz
637 If you want to know more exact memory usage, you should use RSS+CACHE(+SWAP)
638 value in memory.stat(see 5.2).
641 -------------
643 This is similar to numa_maps but operates on a per-memcg basis. This is
645 an memcg since the pages are allowed to be allocated from any physical
650 per-node page counts including "hierarchical_<counter>" which sums up all
651 hierarchical children's values in addition to the memcg's own value.
653 The output format of memory.numa_stat is::
666 The memory controller supports a deep hierarchy and hierarchical accounting.
679 In the diagram above, with hierarchical accounting enabled, all memory
680 usage of e, is accounted to its ancestors up until the root (i.e, c and root).
685 ---------------------------------------
688 accounting is deprecated. An attempt to do it will result in a failure
689 and a warning printed to dmesg.
691 For compatibility reasons writing 1 to memory.use_hierarchy will always pass::
693 # echo 1 > memory.use_hierarchy
698 Soft limits allow for greater sharing of memory. The idea behind soft limits
699 is to allow control groups to use as much of the memory as needed, provided
701 a. There is no memory contention
704 When the system detects memory contention or low memory, control groups
705 are pushed back to their soft limits. If the soft limit of each control
706 group is very high, they are pushed back as much as possible to make
707 sure that one control group does not starve the others of memory.
709 Please note that soft limits is a best-effort feature; it comes with
710 no guarantees, but it does its best to make sure that when memory is
711 heavily contended for, memory is allocated based on the soft limit
716 -------------
721 # echo 256M > memory.soft_limit_in_bytes
723 If we want to change this to 1G, we can at any time use::
725 # echo 1G > memory.soft_limit_in_bytes
729 reclaiming memory for balancing between memory cgroups
732 It is recommended to set the soft limit always below the hard limit,
735 .. _cgroup-v1-memory-move-charges:
742 It's expensive and unreliable! It's better practice to launch workload
744 cgroups to allow fine-grained policy adjustments without having to
748 is, uncharge task's pages from the old cgroup and charge them to the new cgroup.
753 -------------
756 writing to memory.move_charge_at_immigrate of the destination cgroup.
758 If you want to enable it::
760 # echo (some positive value) > memory.move_charge_at_immigrate
765 <cgroup-v1-memory-movable-charges>` for details.
768 Charges are moved only when you move mm->owner, in other words,
773 try to make space by reclaiming memory. Task migration may fail if we
781 # echo 0 > memory.move_charge_at_immigrate
783 .. _cgroup-v1-memory-movable-charges:
786 --------------------------------------
790 a page or a swap can be moved only when it is charged to the task's current
791 (old) memory cgroup.
793 +---+--------------------------------------------------------------------------+
797 | | You must enable Swap Extension (see 2.4) to enable move of swap charges. |
798 +---+--------------------------------------------------------------------------+
799 | 1 | A charge of file pages (normal file, tmpfs file (e.g. ipc shared memory) |
805 | | page_mapcount(page) > 1). You must enable Swap Extension (see 2.4) to |
807 +---+--------------------------------------------------------------------------+
810 --------
812 - All of moving charge operations are done under cgroup_mutex. It's not good
813 behavior to hold the mutex too long, so we may need some trick.
815 9. Memory thresholds
818 Memory cgroup implements memory thresholds using the cgroups notification
819 API (see cgroups.txt). It allows to register multiple memory and memsw
822 To register a threshold, an application must:
824 - create an eventfd using eventfd(2);
825 - open memory.usage_in_bytes or memory.memsw.usage_in_bytes;
826 - write string like "<event_fd> <fd of memory.usage_in_bytes> <threshold>" to
829 Application will be notified through eventfd when memory usage crosses
832 It's applicable for root and non-root cgroup.
834 .. _cgroup-v1-memory-oom-control:
839 memory.oom_control file is for OOM notification and other controls.
841 Memory cgroup implements OOM notifier using the cgroup notification
842 API (See cgroups.txt). It allows to register multiple OOM notification
845 To register a notifier, an application must:
847 - create an eventfd using eventfd(2)
848 - open memory.oom_control file
849 - write string like "<event_fd> <fd of memory.oom_control>" to
855 You can disable the OOM-killer by writing "1" to memory.oom_control file, as:
857 #echo 1 > memory.oom_control
859 If OOM-killer is disabled, tasks under cgroup will hang/sleep
860 in memory cgroup's OOM-waitqueue when they request accountable memory.
862 For running them, you have to relax the memory cgroup's OOM status by
866 To reduce usage,
869 * move some tasks to other group with account migration.
876 - oom_kill_disable 0 or 1
877 (if 1, oom-killer is disabled)
878 - under_oom 0 or 1
879 (if 1, the memory cgroup is under OOM, tasks may be stopped.)
880 - oom_kill integer counter
881 The number of processes belonging to this cgroup killed by any
884 11. Memory Pressure
887 The pressure level notifications can be used to monitor the memory
889 different strategies of managing their memory resources. The pressure
892 The "low" level means that the system is reclaiming memory for new
898 The "medium" level means that the system is experiencing medium memory
900 etc. Upon this event applications may decide to further analyze
901 vmstat/zoneinfo/memcg or internal memory usage statistics and free any
902 resources that can be easily reconstructed or re-read from a disk.
905 about to out of memory (OOM) or even the in-kernel OOM killer is on its
906 way to trigger. Applications should do whatever they can to help the
907 system. It might be too late to consult with vmstat or any other
908 statistics, so it's advisable to take an immediate action.
911 events are not pass-through. For example, you have three cgroups: A->B->C. Now
914 notification, i.e. groups A and B will not receive it. This is done to avoid
916 especially bad if we are low on memory or thrashing. Group B, will receive
921 - "default": this is the default behavior specified above. This mode is the
925 - "hierarchy": events always propagate up to the root, similar to the default
928 example, groups A, B, and C will receive notification of memory pressure.
930 - "local": events are pass-through, i.e. they only receive notifications when
931 memory pressure is experienced in the memcg for which the notification is
933 registered for "local" notification and the group experiences memory
939 specified by a comma-delimited string, i.e. "low,hierarchy" specifies
940 hierarchical, pass-through, notification for all ancestor memcgs. Notification
941 that is the default, non pass-through behavior, does not specify a mode.
942 "medium,local" specifies pass-through notification for the medium level.
944 The file memory.pressure_level is only used to setup an eventfd. To
947 - create an eventfd using eventfd(2);
948 - open memory.pressure_level;
949 - write string as "<event_fd> <fd of memory.pressure_level> <level[,mode]>"
950 to cgroup.event_control.
952 Application will be notified through eventfd when memory pressure is at
953 the specific level (or higher). Read/write operations to
954 memory.pressure_level are no implemented.
959 memory limit, sets up a notification in the cgroup and then makes child
962 # cd /sys/fs/cgroup/memory/
965 # cgroup_event_listener memory.pressure_level low,hierarchy &
966 # echo 8000000 > memory.limit_in_bytes
967 # echo 8000000 > memory.memsw.limit_in_bytes
971 (Expect a bunch of notifications, and eventually, the oom-killer will
977 1. Make per-cgroup scanner reclaim not-shared pages first
978 2. Teach controller to account for shared-pages
985 Overall, the memory controller has been a stable controller and has been
991 .. [1] Singh, Balbir. RFC: Memory Controller, http://lwn.net/Articles/206697/
992 .. [2] Singh, Balbir. Memory Controller (RSS Control),
1008 10. Singh, Balbir. Memory controller v6 test results,
1009 https://lore.kernel.org/r/20070819094658.654.84837.sendpatchset@balbir-laptop
1011 .. [11] Singh, Balbir. Memory controller introduction (v6),
1012 https://lore.kernel.org/r/20070817084228.26003.12568.sendpatchset@balbir-laptop
1013 .. [12] Corbet, Jonathan, Controlling memory use in cgroups,