Lines Matching +full:memory +full:- +full:controller

2 Memory Resource Controller
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
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
34 c. Virtualization solutions can control the amount of memory they want
36 d. A CD/DVD burner could control the amount of memory used by the
38 of available memory.
39 e. There are several other use cases; find one or use the controller just
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
83 memory.stat show various statistics
84 memory.use_hierarchy set/show hierarchical account enabled
87 memory.force_empty trigger forced page reclaim
88 memory.pressure_level set memory pressure notifications
91 memory.swappiness set/show swappiness parameter of vmscan
94 memory.move_charge_at_immigrate This knob is deprecated.
95 memory.oom_control set/show oom controls.
98 memory.numa_stat show the number of memory usage per numa
100 memory.kmem.limit_in_bytes Deprecated knob to set and read the kernel
101 memory hard limit. Kernel hard limit is not
105 Kernel memory is still charged and reported
106 by memory.kmem.usage_in_bytes.
107 memory.kmem.usage_in_bytes show current kernel memory allocation
108 memory.kmem.failcnt show the number of kernel memory usage
110 memory.kmem.max_usage_in_bytes show max kernel memory usage recorded
112 memory.kmem.tcp.limit_in_bytes set/show hard limit for tcp buf memory
115 memory.kmem.tcp.usage_in_bytes show current tcp buf memory allocation
118 memory.kmem.tcp.failcnt show the number of tcp buf memory usage
122 memory.kmem.tcp.max_usage_in_bytes show max tcp buf memory usage recorded
130 The memory controller has a long history. A request for comments for the memory
131 controller was posted by Balbir Singh [1]_. At the time the RFC was posted
132 there were several implementations for memory control. The goal of the
134 for memory control. The first RSS controller was posted by Balbir Singh [2]_
136 of the RSS controller. At OLS, at the resource management BoF, everyone
138 raised to allow user space handling of OOM. The current memory controller is
142 2. Memory Control
145 Memory is a unique resource in the sense that it is present in a limited
148 memory, the same physical memory needs to be reused to accomplish the task.
150 The memory controller implementation has been divided into phases. These
153 1. Memory controller
154 2. mlock(2) controller
155 3. Kernel user memory accounting and slab control
156 4. user mappings length controller
158 The memory controller is the first controller developed.
161 -----------
164 page_counter tracks the current memory usage and limit of the group of
165 processes associated with the controller. Each cgroup has a memory controller
169 ---------------
171 .. code-block::
174 +--------------------+
177 +--------------------+
180 +---------------+ | +---------------+
183 +---------------+ | +---------------+
185 + --------------+
187 +---------------+ +------+--------+
188 | page +----------> page_cgroup|
190 +---------------+ +---------------+
194 Figure 1 shows the important aspects of the controller
205 If everything goes well, a page meta-data-structure called page_cgroup is
207 (*) page_cgroup structure is allocated at boot/memory-hotplug time.
210 ------------------------
225 A swapped-in page is accounted after adding into swapcache.
227 Note: The kernel does swapin-readahead and reads multiple swaps at once.
233 Note: we just account pages-on-LRU because our purpose is to control amount
234 of used pages; not-on-LRU pages tend to be out-of-control from VM view.
237 --------------------------
243 the cgroup that brought it in -- this will happen on memory pressure).
246 --------------------------------------
253 - memory.memsw.usage_in_bytes.
254 - memory.memsw.limit_in_bytes.
256 memsw means memory+swap. Usage of memory+swap is limited by
259 Example: Assume a system with 4G of swap. A task which allocates 6G of memory
260 (by mistake) under 2G memory limitation will use all swap.
265 2.4.1 why 'memory+swap' rather than swap
268 The global LRU(kswapd) can swap out arbitrary pages. Swap-out means
269 to move account from memory to swap...there is no change in usage of
270 memory+swap. In other words, when we want to limit the usage of swap without
271 affecting global LRU, memory+swap limit is better than just limiting swap from
274 2.4.2. What happens when a cgroup hits memory.memsw.limit_in_bytes
277 When a cgroup hits memory.memsw.limit_in_bytes, it's useless to do swap-out
278 in this cgroup. Then, swap-out will not be done by cgroup routine and file
279 caches are dropped. But as mentioned above, global LRU can do swapout memory
280 from it for sanity of the system's memory management state. You can't forbid
284 -----------
288 to reclaim memory from the cgroup so as to make space for the new
291 cgroup. (See :ref:`10. OOM Control <cgroup-v1-memory-oom-control>` below.)
294 pages that are selected for reclaiming come from the per-cgroup LRU
305 (See :ref:`oom_control <cgroup-v1-memory-oom-control>` section)
308 -----------
313 mm->page_table_lock or split pte_lock
314 folio_memcg_lock (memcg->move_lock)
315 mapping->i_pages lock
316 lruvec->lru_lock.
318 Per-node-per-memcgroup LRU (cgroup's private LRU) is guarded by
319 lruvec->lru_lock; the folio LRU flag is cleared before
320 isolating a page from its LRU under lruvec->lru_lock.
322 .. _cgroup-v1-memory-kernel-extension:
324 2.7 Kernel Memory Extension
325 -----------------------------------------------
327 With the Kernel memory extension, the Memory Controller is able to limit
328 the amount of kernel memory used by the system. Kernel memory is fundamentally
329 different than user memory, since it can't be swapped out, which makes it
332 Kernel memory accounting is enabled for all memory cgroups by default. But
333 it can be disabled system-wide by passing cgroup.memory=nokmem to the kernel
334 at boot time. In this case, kernel memory will not be accounted at all.
336 Kernel memory limits are not imposed for the root cgroup. Usage for the root
337 cgroup may or may not be accounted. The memory used is accumulated into
338 memory.kmem.usage_in_bytes, or in a separate counter when it makes sense.
344 Currently no soft limit is implemented for kernel memory. It is future work
347 2.7.1 Current Kernel Memory resources accounted
348 -----------------------------------------------
352 kernel memory, we prevent new processes from being created when the kernel
353 memory usage is too high.
363 sockets memory pressure:
364 some sockets protocols have memory pressure
365 thresholds. The Memory Controller allows them to be controlled individually
368 tcp memory pressure:
369 sockets memory pressure for the tcp protocol.
372 ----------------------
374 Because the "kmem" counter is fed to the main user counter, kernel memory can
375 never be limited completely independently of user memory. Say "U" is the user
381 accounting. Kernel memory is completely ignored.
384 Kernel memory is a subset of the user memory. This setup is useful in
385 deployments where the total amount of memory per-cgroup is overcommitted.
386 Overcommitting kernel memory limits is definitely not recommended, since the
387 box can still run out of non-reclaimable memory.
389 never greater than the total memory, and freely set U at the cost of his
393 In the current implementation, memory reclaim will NOT be triggered for
399 triggered for the cgroup for both kinds of memory. This setup gives the
400 admin a unified view of memory, and it is also useful for people who just
401 want to track kernel memory usage.
410 <cgroups-why-needed>` for the background information)::
412 # mount -t tmpfs none /sys/fs/cgroup
413 # mkdir /sys/fs/cgroup/memory
414 # mount -t cgroup none /sys/fs/cgroup/memory -o memory
418 # mkdir /sys/fs/cgroup/memory/0
419 # echo $$ > /sys/fs/cgroup/memory/0/tasks
421 4. Since now we're in the 0 cgroup, we can alter the memory limit::
423 # echo 4M > /sys/fs/cgroup/memory/0/memory.limit_in_bytes
427 # cat /sys/fs/cgroup/memory/0/memory.limit_in_bytes
436 We can write "-1" to reset the ``*.limit_in_bytes(unlimited)``.
444 # cat /sys/fs/cgroup/memory/0/memory.usage_in_bytes
450 availability of memory on the system. The user is required to re-read
453 # echo 1 > memory.limit_in_bytes
454 # cat memory.limit_in_bytes
457 The memory.failcnt field gives the number of times that the cgroup limit was
460 The memory.stat file gives accounting information. Now, the number of
468 Performance test is also important. To see pure memory controller's overhead,
472 Page-fault scalability is also important. At measuring parallel
473 page fault test, multi-process test may be better than multi-thread
477 Trying usual test under memory controller is always helpful.
479 .. _cgroup-v1-memory-test-troubleshoot:
482 -------------------
488 2. The user is using anonymous memory and swap is turned off or too low
494 <cgroup-v1-memory-oom-control>` (below) and seeing what happens will be
497 .. _cgroup-v1-memory-test-task-migration:
500 ------------------
508 See :ref:`8. "Move charges at task migration" <cgroup-v1-memory-move-charges>`
511 ---------------------
514 <cgroup-v1-memory-test-troubleshoot>` and :ref:`4.2
515 <cgroup-v1-memory-test-task-migration>`, a cgroup might have some charge
530 ---------------
531 memory.force_empty interface is provided to make cgroup's memory usage empty.
534 # echo 0 > memory.force_empty
540 charged file caches. Some out-of-use page caches may keep charged until
541 memory pressure happens. If you want to avoid that, force_empty will be useful.
544 -------------
546 memory.stat file includes following statistics:
548 * per-memory cgroup local status
551 cache # of bytes of page cache memory.
552 rss # of bytes of anonymous and swap cache memory (includes
556 pgpgin # of charging events to the memory cgroup. The charging
559 pgpgout # of uncharging events to the memory cgroup. The uncharging
563 swapcached # of bytes of swap cached in memory
567 inactive_anon # of bytes of anonymous and swap cache memory on inactive
569 active_anon # of bytes of anonymous and swap cache memory on active
571 inactive_file # of bytes of file-backed memory and MADV_FREE anonymous
572 memory (LazyFree pages) on inactive LRU list.
573 active_file # of bytes of file-backed memory on active LRU list.
574 unevictable # of bytes of memory that cannot be reclaimed (mlocked etc).
577 * status considering hierarchy (see memory.use_hierarchy settings):
580 hierarchical_memory_limit # of bytes of memory limit with regard to
582 under which the memory cgroup is
583 hierarchical_memsw_limit # of bytes of memory+swap limit with regard to
584 hierarchy under which memory cgroup is.
607 Only anonymous and swap cache memory is listed as part of 'rss' stat.
609 amount of physical memory used by the cgroup.
615 only some, but not all that memory is mapped.
618 mapped_file is accounted only when the memory cgroup is owner of page
622 --------------
633 -----------
635 A memory cgroup provides memory.failcnt and memory.memsw.failcnt files.
637 hit its limit. When a memory cgroup hits a limit, failcnt increases and
638 memory under it will be reclaimed.
642 # echo 0 > .../memory.failcnt
645 ------------------
647 For efficiency, as other kernel components, memory cgroup uses some optimization
649 method and doesn't show 'exact' value of memory (and swap) usage, it's a fuzz
651 If you want to know more exact memory usage, you should use RSS+CACHE(+SWAP)
652 value in memory.stat(see 5.2).
655 -------------
657 This is similar to numa_maps but operates on a per-memcg basis. This is
664 per-node page counts including "hierarchical_<counter>" which sums up all
667 The output format of memory.numa_stat is::
680 The memory controller supports a deep hierarchy and hierarchical accounting.
693 In the diagram above, with hierarchical accounting enabled, all memory
699 ---------------------------------------
705 For compatibility reasons writing 1 to memory.use_hierarchy will always pass::
707 # echo 1 > memory.use_hierarchy
714 Soft limits allow for greater sharing of memory. The idea behind soft limits
715 is to allow control groups to use as much of the memory as needed, provided
717 a. There is no memory contention
720 When the system detects memory contention or low memory, control groups
723 sure that one control group does not starve the others of memory.
725 Please note that soft limits is a best-effort feature; it comes with
726 no guarantees, but it does its best to make sure that when memory is
727 heavily contended for, memory is allocated based on the soft limit
732 -------------
737 # echo 256M > memory.soft_limit_in_bytes
741 # echo 1G > memory.soft_limit_in_bytes
745 reclaiming memory for balancing between memory cgroups
751 .. _cgroup-v1-memory-move-charges:
758 Reading memory.move_charge_at_immigrate will always return 0 and writing
759 to it will always return -EINVAL.
761 9. Memory thresholds
764 Memory cgroup implements memory thresholds using the cgroups notification
765 API (see cgroups.txt). It allows to register multiple memory and memsw
770 - create an eventfd using eventfd(2);
771 - open memory.usage_in_bytes or memory.memsw.usage_in_bytes;
772 - write string like "<event_fd> <fd of memory.usage_in_bytes> <threshold>" to
775 Application will be notified through eventfd when memory usage crosses
778 It's applicable for root and non-root cgroup.
780 .. _cgroup-v1-memory-oom-control:
787 memory.oom_control file is for OOM notification and other controls.
789 Memory cgroup implements OOM notifier using the cgroup notification
795 - create an eventfd using eventfd(2)
796 - open memory.oom_control file
797 - write string like "<event_fd> <fd of memory.oom_control>" to
803 You can disable the OOM-killer by writing "1" to memory.oom_control file, as:
805 #echo 1 > memory.oom_control
807 If OOM-killer is disabled, tasks under cgroup will hang/sleep
808 in memory cgroup's OOM-waitqueue when they request accountable memory.
810 For running them, you have to relax the memory cgroup's OOM status by
824 - oom_kill_disable 0 or 1
825 (if 1, oom-killer is disabled)
826 - under_oom 0 or 1
827 (if 1, the memory cgroup is under OOM, tasks may be stopped.)
828 - oom_kill integer counter
832 11. Memory Pressure (DEPRECATED)
837 The pressure level notifications can be used to monitor the memory
839 different strategies of managing their memory resources. The pressure
842 The "low" level means that the system is reclaiming memory for new
848 The "medium" level means that the system is experiencing medium memory
851 vmstat/zoneinfo/memcg or internal memory usage statistics and free any
852 resources that can be easily reconstructed or re-read from a disk.
855 about to out of memory (OOM) or even the in-kernel OOM killer is on its
861 events are not pass-through. For example, you have three cgroups: A->B->C. Now
866 especially bad if we are low on memory or thrashing. Group B, will receive
871 - "default": this is the default behavior specified above. This mode is the
875 - "hierarchy": events always propagate up to the root, similar to the default
878 example, groups A, B, and C will receive notification of memory pressure.
880 - "local": events are pass-through, i.e. they only receive notifications when
881 memory pressure is experienced in the memcg for which the notification is
883 registered for "local" notification and the group experiences memory
889 specified by a comma-delimited string, i.e. "low,hierarchy" specifies
890 hierarchical, pass-through, notification for all ancestor memcgs. Notification
891 that is the default, non pass-through behavior, does not specify a mode.
892 "medium,local" specifies pass-through notification for the medium level.
894 The file memory.pressure_level is only used to setup an eventfd. To
897 - create an eventfd using eventfd(2);
898 - open memory.pressure_level;
899 - write string as "<event_fd> <fd of memory.pressure_level> <level[,mode]>"
902 Application will be notified through eventfd when memory pressure is at
904 memory.pressure_level are no implemented.
909 memory limit, sets up a notification in the cgroup and then makes child
912 # cd /sys/fs/cgroup/memory/
915 # cgroup_event_listener memory.pressure_level low,hierarchy &
916 # echo 8000000 > memory.limit_in_bytes
917 # echo 8000000 > memory.memsw.limit_in_bytes
921 (Expect a bunch of notifications, and eventually, the oom-killer will
927 1. Make per-cgroup scanner reclaim not-shared pages first
928 2. Teach controller to account for shared-pages
935 Overall, the memory controller has been a stable controller and has been
941 .. [1] Singh, Balbir. RFC: Memory Controller, http://lwn.net/Articles/206697/
942 .. [2] Singh, Balbir. Memory Controller (RSS Control),
946 .. [4] Emelianov, Pavel. RSS controller based on process cgroups (v2)
948 .. [5] Emelianov, Pavel. RSS controller based on process cgroups (v3)
954 8. Singh, Balbir. RSS controller v2 test results (lmbench),
956 9. Singh, Balbir. RSS controller v2 AIM9 results
958 10. Singh, Balbir. Memory controller v6 test results,
959 https://lore.kernel.org/r/20070819094658.654.84837.sendpatchset@balbir-laptop
961 .. [11] Singh, Balbir. Memory controller introduction (v6),
962 https://lore.kernel.org/r/20070817084228.26003.12568.sendpatchset@balbir-laptop
963 .. [12] Corbet, Jonathan, Controlling memory use in cgroups,