4 October, 2015 Tejun Heo <tj@kernel.org>
6 This is the authoritative documentation on the design, interface and
7 conventions of cgroup v2. It describes all userland-visible aspects
8 of cgroup including core and specific controller behaviors. All
9 future changes must be reflected in this document. Documentation for
10 v1 is available under Documentation/cgroup-v1/.
19 2-2. Organizing Processes
20 2-3. [Un]populated Notification
21 2-4. Controlling Controllers
22 2-4-1. Enabling and Disabling
23 2-4-2. Top-down Constraint
24 2-4-3. No Internal Process Constraint
26 2-5-1. Model of Delegation
27 2-5-2. Delegation Containment
29 2-6-1. Organize Once and Control
30 2-6-2. Avoid Name Collisions
31 3. Resource Distribution Models
39 4-3. Core Interface Files
42 5-1-1. CPU Interface Files
44 5-2-1. Memory Interface Files
45 5-2-2. Usage Guidelines
46 5-2-3. Memory Ownership
48 5-3-1. IO Interface Files
50 P. Information on Kernel Programming
51 P-1. Filesystem Support for Writeback
52 D. Deprecated v1 Core Features
53 R. Issues with v1 and Rationales for v2
54 R-1. Multiple Hierarchies
55 R-2. Thread Granularity
56 R-3. Competition Between Inner Nodes and Threads
57 R-4. Other Interface Issues
58 R-5. Controller Issues and Remedies
66 "cgroup" stands for "control group" and is never capitalized. The
67 singular form is used to designate the whole feature and also as a
68 qualifier as in "cgroup controllers". When explicitly referring to
69 multiple individual control groups, the plural form "cgroups" is used.
74 cgroup is a mechanism to organize processes hierarchically and
75 distribute system resources along the hierarchy in a controlled and
78 cgroup is largely composed of two parts - the core and controllers.
79 cgroup core is primarily responsible for hierarchically organizing
80 processes. A cgroup controller is usually responsible for
81 distributing a specific type of system resource along the hierarchy
82 although there are utility controllers which serve purposes other than
83 resource distribution.
85 cgroups form a tree structure and every process in the system belongs
86 to one and only one cgroup. All threads of a process belong to the
87 same cgroup. On creation, all processes are put in the cgroup that
88 the parent process belongs to at the time. A process can be migrated
89 to another cgroup. Migration of a process doesn't affect already
90 existing descendant processes.
92 Following certain structural constraints, controllers may be enabled or
93 disabled selectively on a cgroup. All controller behaviors are
94 hierarchical - if a controller is enabled on a cgroup, it affects all
95 processes which belong to the cgroups consisting the inclusive
96 sub-hierarchy of the cgroup. When a controller is enabled on a nested
97 cgroup, it always restricts the resource distribution further. The
98 restrictions set closer to the root in the hierarchy can not be
99 overridden from further away.
106 Unlike v1, cgroup v2 has only single hierarchy. The cgroup v2
107 hierarchy can be mounted with the following mount command.
109 # mount -t cgroup2 none $MOUNT_POINT
111 cgroup2 filesystem has the magic number 0x63677270 ("cgrp"). All
112 controllers which support v2 and are not bound to a v1 hierarchy are
113 automatically bound to the v2 hierarchy and show up at the root.
114 Controllers which are not in active use in the v2 hierarchy can be
115 bound to other hierarchies. This allows mixing v2 hierarchy with the
116 legacy v1 multiple hierarchies in a fully backward compatible way.
118 A controller can be moved across hierarchies only after the controller
119 is no longer referenced in its current hierarchy. Because per-cgroup
120 controller states are destroyed asynchronously and controllers may
121 have lingering references, a controller may not show up immediately on
122 the v2 hierarchy after the final umount of the previous hierarchy.
123 Similarly, a controller should be fully disabled to be moved out of
124 the unified hierarchy and it may take some time for the disabled
125 controller to become available for other hierarchies; furthermore, due
126 to inter-controller dependencies, other controllers may need to be
129 While useful for development and manual configurations, moving
130 controllers dynamically between the v2 and other hierarchies is
131 strongly discouraged for production use. It is recommended to decide
132 the hierarchies and controller associations before starting using the
133 controllers after system boot.
136 2-2. Organizing Processes
138 Initially, only the root cgroup exists to which all processes belong.
139 A child cgroup can be created by creating a sub-directory.
143 A given cgroup may have multiple child cgroups forming a tree
144 structure. Each cgroup has a read-writable interface file
145 "cgroup.procs". When read, it lists the PIDs of all processes which
146 belong to the cgroup one-per-line. The PIDs are not ordered and the
147 same PID may show up more than once if the process got moved to
148 another cgroup and then back or the PID got recycled while reading.
150 A process can be migrated into a cgroup by writing its PID to the
151 target cgroup's "cgroup.procs" file. Only one process can be migrated
152 on a single write(2) call. If a process is composed of multiple
153 threads, writing the PID of any thread migrates all threads of the
156 When a process forks a child process, the new process is born into the
157 cgroup that the forking process belongs to at the time of the
158 operation. After exit, a process stays associated with the cgroup
159 that it belonged to at the time of exit until it's reaped; however, a
160 zombie process does not appear in "cgroup.procs" and thus can't be
161 moved to another cgroup.
163 A cgroup which doesn't have any children or live processes can be
164 destroyed by removing the directory. Note that a cgroup which doesn't
165 have any children and is associated only with zombie processes is
166 considered empty and can be removed.
170 "/proc/$PID/cgroup" lists a process's cgroup membership. If legacy
171 cgroup is in use in the system, this file may contain multiple lines,
172 one for each hierarchy. The entry for cgroup v2 is always in the
175 # cat /proc/842/cgroup
177 0::/test-cgroup/test-cgroup-nested
179 If the process becomes a zombie and the cgroup it was associated with
180 is removed subsequently, " (deleted)" is appended to the path.
182 # cat /proc/842/cgroup
184 0::/test-cgroup/test-cgroup-nested (deleted)
187 2-3. [Un]populated Notification
189 Each non-root cgroup has a "cgroup.events" file which contains
190 "populated" field indicating whether the cgroup's sub-hierarchy has
191 live processes in it. Its value is 0 if there is no live process in
192 the cgroup and its descendants; otherwise, 1. poll and [id]notify
193 events are triggered when the value changes. This can be used, for
194 example, to start a clean-up operation after all processes of a given
195 sub-hierarchy have exited. The populated state updates and
196 notifications are recursive. Consider the following sub-hierarchy
197 where the numbers in the parentheses represent the numbers of processes
203 A, B and C's "populated" fields would be 1 while D's 0. After the one
204 process in C exits, B and C's "populated" fields would flip to "0" and
205 file modified events will be generated on the "cgroup.events" files of
209 2-4. Controlling Controllers
211 2-4-1. Enabling and Disabling
213 Each cgroup has a "cgroup.controllers" file which lists all
214 controllers available for the cgroup to enable.
216 # cat cgroup.controllers
219 No controller is enabled by default. Controllers can be enabled and
220 disabled by writing to the "cgroup.subtree_control" file.
222 # echo "+cpu +memory -io" > cgroup.subtree_control
224 Only controllers which are listed in "cgroup.controllers" can be
225 enabled. When multiple operations are specified as above, either they
226 all succeed or fail. If multiple operations on the same controller
227 are specified, the last one is effective.
229 Enabling a controller in a cgroup indicates that the distribution of
230 the target resource across its immediate children will be controlled.
231 Consider the following sub-hierarchy. The enabled controllers are
232 listed in parentheses.
234 A(cpu,memory) - B(memory) - C()
237 As A has "cpu" and "memory" enabled, A will control the distribution
238 of CPU cycles and memory to its children, in this case, B. As B has
239 "memory" enabled but not "CPU", C and D will compete freely on CPU
240 cycles but their division of memory available to B will be controlled.
242 As a controller regulates the distribution of the target resource to
243 the cgroup's children, enabling it creates the controller's interface
244 files in the child cgroups. In the above example, enabling "cpu" on B
245 would create the "cpu." prefixed controller interface files in C and
246 D. Likewise, disabling "memory" from B would remove the "memory."
247 prefixed controller interface files from C and D. This means that the
248 controller interface files - anything which doesn't start with
249 "cgroup." are owned by the parent rather than the cgroup itself.
252 2-4-2. Top-down Constraint
254 Resources are distributed top-down and a cgroup can further distribute
255 a resource only if the resource has been distributed to it from the
256 parent. This means that all non-root "cgroup.subtree_control" files
257 can only contain controllers which are enabled in the parent's
258 "cgroup.subtree_control" file. A controller can be enabled only if
259 the parent has the controller enabled and a controller can't be
260 disabled if one or more children have it enabled.
263 2-4-3. No Internal Process Constraint
265 Non-root cgroups can only distribute resources to their children when
266 they don't have any processes of their own. In other words, only
267 cgroups which don't contain any processes can have controllers enabled
268 in their "cgroup.subtree_control" files.
270 This guarantees that, when a controller is looking at the part of the
271 hierarchy which has it enabled, processes are always only on the
272 leaves. This rules out situations where child cgroups compete against
273 internal processes of the parent.
275 The root cgroup is exempt from this restriction. Root contains
276 processes and anonymous resource consumption which can't be associated
277 with any other cgroups and requires special treatment from most
278 controllers. How resource consumption in the root cgroup is governed
279 is up to each controller.
281 Note that the restriction doesn't get in the way if there is no
282 enabled controller in the cgroup's "cgroup.subtree_control". This is
283 important as otherwise it wouldn't be possible to create children of a
284 populated cgroup. To control resource distribution of a cgroup, the
285 cgroup must create children and transfer all its processes to the
286 children before enabling controllers in its "cgroup.subtree_control"
292 2-5-1. Model of Delegation
294 A cgroup can be delegated to a less privileged user by granting write
295 access of the directory and its "cgroup.procs" file to the user. Note
296 that resource control interface files in a given directory control the
297 distribution of the parent's resources and thus must not be delegated
298 along with the directory.
300 Once delegated, the user can build sub-hierarchy under the directory,
301 organize processes as it sees fit and further distribute the resources
302 it received from the parent. The limits and other settings of all
303 resource controllers are hierarchical and regardless of what happens
304 in the delegated sub-hierarchy, nothing can escape the resource
305 restrictions imposed by the parent.
307 Currently, cgroup doesn't impose any restrictions on the number of
308 cgroups in or nesting depth of a delegated sub-hierarchy; however,
309 this may be limited explicitly in the future.
312 2-5-2. Delegation Containment
314 A delegated sub-hierarchy is contained in the sense that processes
315 can't be moved into or out of the sub-hierarchy by the delegatee. For
316 a process with a non-root euid to migrate a target process into a
317 cgroup by writing its PID to the "cgroup.procs" file, the following
318 conditions must be met.
320 - The writer's euid must match either uid or suid of the target process.
322 - The writer must have write access to the "cgroup.procs" file.
324 - The writer must have write access to the "cgroup.procs" file of the
325 common ancestor of the source and destination cgroups.
327 The above three constraints ensure that while a delegatee may migrate
328 processes around freely in the delegated sub-hierarchy it can't pull
329 in from or push out to outside the sub-hierarchy.
331 For an example, let's assume cgroups C0 and C1 have been delegated to
332 user U0 who created C00, C01 under C0 and C10 under C1 as follows and
333 all processes under C0 and C1 belong to U0.
335 ~~~~~~~~~~~~~ - C0 - C00
338 ~~~~~~~~~~~~~ - C1 - C10
340 Let's also say U0 wants to write the PID of a process which is
341 currently in C10 into "C00/cgroup.procs". U0 has write access to the
342 file and uid match on the process; however, the common ancestor of the
343 source cgroup C10 and the destination cgroup C00 is above the points
344 of delegation and U0 would not have write access to its "cgroup.procs"
345 files and thus the write will be denied with -EACCES.
350 2-6-1. Organize Once and Control
352 Migrating a process across cgroups is a relatively expensive operation
353 and stateful resources such as memory are not moved together with the
354 process. This is an explicit design decision as there often exist
355 inherent trade-offs between migration and various hot paths in terms
356 of synchronization cost.
358 As such, migrating processes across cgroups frequently as a means to
359 apply different resource restrictions is discouraged. A workload
360 should be assigned to a cgroup according to the system's logical and
361 resource structure once on start-up. Dynamic adjustments to resource
362 distribution can be made by changing controller configuration through
366 2-6-2. Avoid Name Collisions
368 Interface files for a cgroup and its children cgroups occupy the same
369 directory and it is possible to create children cgroups which collide
370 with interface files.
372 All cgroup core interface files are prefixed with "cgroup." and each
373 controller's interface files are prefixed with the controller name and
374 a dot. A controller's name is composed of lower case alphabets and
375 '_'s but never begins with an '_' so it can be used as the prefix
376 character for collision avoidance. Also, interface file names won't
377 start or end with terms which are often used in categorizing workloads
378 such as job, service, slice, unit or workload.
380 cgroup doesn't do anything to prevent name collisions and it's the
381 user's responsibility to avoid them.
384 3. Resource Distribution Models
386 cgroup controllers implement several resource distribution schemes
387 depending on the resource type and expected use cases. This section
388 describes major schemes in use along with their expected behaviors.
393 A parent's resource is distributed by adding up the weights of all
394 active children and giving each the fraction matching the ratio of its
395 weight against the sum. As only children which can make use of the
396 resource at the moment participate in the distribution, this is
397 work-conserving. Due to the dynamic nature, this model is usually
398 used for stateless resources.
400 All weights are in the range [1, 10000] with the default at 100. This
401 allows symmetric multiplicative biases in both directions at fine
402 enough granularity while staying in the intuitive range.
404 As long as the weight is in range, all configuration combinations are
405 valid and there is no reason to reject configuration changes or
408 "cpu.weight" proportionally distributes CPU cycles to active children
409 and is an example of this type.
414 A child can only consume upto the configured amount of the resource.
415 Limits can be over-committed - the sum of the limits of children can
416 exceed the amount of resource available to the parent.
418 Limits are in the range [0, max] and defaults to "max", which is noop.
420 As limits can be over-committed, all configuration combinations are
421 valid and there is no reason to reject configuration changes or
424 "io.max" limits the maximum BPS and/or IOPS that a cgroup can consume
425 on an IO device and is an example of this type.
430 A cgroup is protected to be allocated upto the configured amount of
431 the resource if the usages of all its ancestors are under their
432 protected levels. Protections can be hard guarantees or best effort
433 soft boundaries. Protections can also be over-committed in which case
434 only upto the amount available to the parent is protected among
437 Protections are in the range [0, max] and defaults to 0, which is
440 As protections can be over-committed, all configuration combinations
441 are valid and there is no reason to reject configuration changes or
444 "memory.low" implements best-effort memory protection and is an
445 example of this type.
450 A cgroup is exclusively allocated a certain amount of a finite
451 resource. Allocations can't be over-committed - the sum of the
452 allocations of children can not exceed the amount of resource
453 available to the parent.
455 Allocations are in the range [0, max] and defaults to 0, which is no
458 As allocations can't be over-committed, some configuration
459 combinations are invalid and should be rejected. Also, if the
460 resource is mandatory for execution of processes, process migrations
463 "cpu.rt.max" hard-allocates realtime slices and is an example of this
471 All interface files should be in one of the following formats whenever
474 New-line separated values
475 (when only one value can be written at once)
481 Space separated values
482 (when read-only or multiple values can be written at once)
494 KEY0 SUB_KEY0=VAL00 SUB_KEY1=VAL01...
495 KEY1 SUB_KEY0=VAL10 SUB_KEY1=VAL11...
498 For a writable file, the format for writing should generally match
499 reading; however, controllers may allow omitting later fields or
500 implement restricted shortcuts for most common use cases.
502 For both flat and nested keyed files, only the values for a single key
503 can be written at a time. For nested keyed files, the sub key pairs
504 may be specified in any order and not all pairs have to be specified.
509 - Settings for a single feature should be contained in a single file.
511 - The root cgroup should be exempt from resource control and thus
512 shouldn't have resource control interface files. Also,
513 informational files on the root cgroup which end up showing global
514 information available elsewhere shouldn't exist.
516 - If a controller implements weight based resource distribution, its
517 interface file should be named "weight" and have the range [1,
518 10000] with 100 as the default. The values are chosen to allow
519 enough and symmetric bias in both directions while keeping it
520 intuitive (the default is 100%).
522 - If a controller implements an absolute resource guarantee and/or
523 limit, the interface files should be named "min" and "max"
524 respectively. If a controller implements best effort resource
525 guarantee and/or limit, the interface files should be named "low"
526 and "high" respectively.
528 In the above four control files, the special token "max" should be
529 used to represent upward infinity for both reading and writing.
531 - If a setting has a configurable default value and keyed specific
532 overrides, the default entry should be keyed with "default" and
533 appear as the first entry in the file.
535 The default value can be updated by writing either "default $VAL" or
538 When writing to update a specific override, "default" can be used as
539 the value to indicate removal of the override. Override entries
540 with "default" as the value must not appear when read.
542 For example, a setting which is keyed by major:minor device numbers
543 with integer values may look like the following.
545 # cat cgroup-example-interface-file
549 The default value can be updated by
551 # echo 125 > cgroup-example-interface-file
555 # echo "default 125" > cgroup-example-interface-file
557 An override can be set by
559 # echo "8:16 170" > cgroup-example-interface-file
563 # echo "8:0 default" > cgroup-example-interface-file
564 # cat cgroup-example-interface-file
568 - For events which are not very high frequency, an interface file
569 "events" should be created which lists event key value pairs.
570 Whenever a notifiable event happens, file modified event should be
571 generated on the file.
574 4-3. Core Interface Files
576 All cgroup core files are prefixed with "cgroup."
580 A read-write new-line separated values file which exists on
583 When read, it lists the PIDs of all processes which belong to
584 the cgroup one-per-line. The PIDs are not ordered and the
585 same PID may show up more than once if the process got moved
586 to another cgroup and then back or the PID got recycled while
589 A PID can be written to migrate the process associated with
590 the PID to the cgroup. The writer should match all of the
591 following conditions.
593 - Its euid is either root or must match either uid or suid of
596 - It must have write access to the "cgroup.procs" file.
598 - It must have write access to the "cgroup.procs" file of the
599 common ancestor of the source and destination cgroups.
601 When delegating a sub-hierarchy, write access to this file
602 should be granted along with the containing directory.
606 A read-only space separated values file which exists on all
609 It shows space separated list of all controllers available to
610 the cgroup. The controllers are not ordered.
612 cgroup.subtree_control
614 A read-write space separated values file which exists on all
615 cgroups. Starts out empty.
617 When read, it shows space separated list of the controllers
618 which are enabled to control resource distribution from the
619 cgroup to its children.
621 Space separated list of controllers prefixed with '+' or '-'
622 can be written to enable or disable controllers. A controller
623 name prefixed with '+' enables the controller and '-'
624 disables. If a controller appears more than once on the list,
625 the last one is effective. When multiple enable and disable
626 operations are specified, either all succeed or all fail.
630 A read-only flat-keyed file which exists on non-root cgroups.
631 The following entries are defined. Unless specified
632 otherwise, a value change in this file generates a file
637 1 if the cgroup or its descendants contains any live
638 processes; otherwise, 0.
645 [NOTE: The interface for the cpu controller hasn't been merged yet]
647 The "cpu" controllers regulates distribution of CPU cycles. This
648 controller implements weight and absolute bandwidth limit models for
649 normal scheduling policy and absolute bandwidth allocation model for
650 realtime scheduling policy.
653 5-1-1. CPU Interface Files
655 All time durations are in microseconds.
659 A read-only flat-keyed file which exists on non-root cgroups.
661 It reports the following six stats.
672 A read-write single value file which exists on non-root
673 cgroups. The default is "100".
675 The weight in the range [1, 10000].
679 A read-write two value file which exists on non-root cgroups.
680 The default is "max 100000".
682 The maximum bandwidth limit. It's in the following format.
686 which indicates that the group may consume upto $MAX in each
687 $PERIOD duration. "max" for $MAX indicates no limit. If only
688 one number is written, $MAX is updated.
692 [NOTE: The semantics of this file is still under discussion and the
693 interface hasn't been merged yet]
695 A read-write two value file which exists on all cgroups.
696 The default is "0 100000".
698 The maximum realtime runtime allocation. Over-committing
699 configurations are disallowed and process migrations are
700 rejected if not enough bandwidth is available. It's in the
705 which indicates that the group may consume upto $MAX in each
706 $PERIOD duration. If only one number is written, $MAX is
712 The "memory" controller regulates distribution of memory. Memory is
713 stateful and implements both limit and protection models. Due to the
714 intertwining between memory usage and reclaim pressure and the
715 stateful nature of memory, the distribution model is relatively
718 While not completely water-tight, all major memory usages by a given
719 cgroup are tracked so that the total memory consumption can be
720 accounted and controlled to a reasonable extent. Currently, the
721 following types of memory usages are tracked.
723 - Userland memory - page cache and anonymous memory.
725 - Kernel data structures such as dentries and inodes.
727 - TCP socket buffers.
729 The above list may expand in the future for better coverage.
732 5-2-1. Memory Interface Files
734 All memory amounts are in bytes. If a value which is not aligned to
735 PAGE_SIZE is written, the value may be rounded up to the closest
736 PAGE_SIZE multiple when read back.
740 A read-only single value file which exists on non-root
743 The total amount of memory currently being used by the cgroup
748 A read-write single value file which exists on non-root
749 cgroups. The default is "0".
751 Best-effort memory protection. If the memory usages of a
752 cgroup and all its ancestors are below their low boundaries,
753 the cgroup's memory won't be reclaimed unless memory can be
754 reclaimed from unprotected cgroups.
756 Putting more memory than generally available under this
757 protection is discouraged.
761 A read-write single value file which exists on non-root
762 cgroups. The default is "max".
764 Memory usage throttle limit. This is the main mechanism to
765 control memory usage of a cgroup. If a cgroup's usage goes
766 over the high boundary, the processes of the cgroup are
767 throttled and put under heavy reclaim pressure.
769 Going over the high limit never invokes the OOM killer and
770 under extreme conditions the limit may be breached.
774 A read-write single value file which exists on non-root
775 cgroups. The default is "max".
777 Memory usage hard limit. This is the final protection
778 mechanism. If a cgroup's memory usage reaches this limit and
779 can't be reduced, the OOM killer is invoked in the cgroup.
780 Under certain circumstances, the usage may go over the limit
783 This is the ultimate protection mechanism. As long as the
784 high limit is used and monitored properly, this limit's
785 utility is limited to providing the final safety net.
789 A read-only flat-keyed file which exists on non-root cgroups.
790 The following entries are defined. Unless specified
791 otherwise, a value change in this file generates a file
796 The number of times the cgroup is reclaimed due to
797 high memory pressure even though its usage is under
798 the low boundary. This usually indicates that the low
799 boundary is over-committed.
803 The number of times processes of the cgroup are
804 throttled and routed to perform direct memory reclaim
805 because the high memory boundary was exceeded. For a
806 cgroup whose memory usage is capped by the high limit
807 rather than global memory pressure, this event's
808 occurrences are expected.
812 The number of times the cgroup's memory usage was
813 about to go over the max boundary. If direct reclaim
814 fails to bring it down, the OOM killer is invoked.
818 The number of times the OOM killer has been invoked in
819 the cgroup. This may not exactly match the number of
820 processes killed but should generally be close.
824 A read-only flat-keyed file which exists on non-root cgroups.
826 This breaks down the cgroup's memory footprint into different
827 types of memory, type-specific details, and other information
828 on the state and past events of the memory management system.
830 All memory amounts are in bytes.
832 The entries are ordered to be human readable, and new entries
833 can show up in the middle. Don't rely on items remaining in a
834 fixed position; use the keys to look up specific values!
838 Amount of memory used in anonymous mappings such as
839 brk(), sbrk(), and mmap(MAP_ANONYMOUS)
843 Amount of memory used to cache filesystem data,
844 including tmpfs and shared memory.
848 Amount of memory used for storing in-kernel data
853 Amount of memory used in network transmission buffers
857 Amount of cached filesystem data mapped with mmap()
861 Amount of cached filesystem data that was modified but
862 not yet written back to disk
866 Amount of cached filesystem data that was modified and
867 is currently being written back to disk
875 Amount of memory, swap-backed and filesystem-backed,
876 on the internal memory management lists used by the
877 page reclaim algorithm
881 Part of "slab" that might be reclaimed, such as
886 Part of "slab" that cannot be reclaimed on memory
891 Total number of page faults incurred
895 Number of major page faults incurred
899 A read-only single value file which exists on non-root
902 The total amount of swap currently being used by the cgroup
907 A read-write single value file which exists on non-root
908 cgroups. The default is "max".
910 Swap usage hard limit. If a cgroup's swap usage reaches this
911 limit, anonymous meomry of the cgroup will not be swapped out.
916 "memory.high" is the main mechanism to control memory usage.
917 Over-committing on high limit (sum of high limits > available memory)
918 and letting global memory pressure to distribute memory according to
919 usage is a viable strategy.
921 Because breach of the high limit doesn't trigger the OOM killer but
922 throttles the offending cgroup, a management agent has ample
923 opportunities to monitor and take appropriate actions such as granting
924 more memory or terminating the workload.
926 Determining whether a cgroup has enough memory is not trivial as
927 memory usage doesn't indicate whether the workload can benefit from
928 more memory. For example, a workload which writes data received from
929 network to a file can use all available memory but can also operate as
930 performant with a small amount of memory. A measure of memory
931 pressure - how much the workload is being impacted due to lack of
932 memory - is necessary to determine whether a workload needs more
933 memory; unfortunately, memory pressure monitoring mechanism isn't
937 5-2-3. Memory Ownership
939 A memory area is charged to the cgroup which instantiated it and stays
940 charged to the cgroup until the area is released. Migrating a process
941 to a different cgroup doesn't move the memory usages that it
942 instantiated while in the previous cgroup to the new cgroup.
944 A memory area may be used by processes belonging to different cgroups.
945 To which cgroup the area will be charged is in-deterministic; however,
946 over time, the memory area is likely to end up in a cgroup which has
947 enough memory allowance to avoid high reclaim pressure.
949 If a cgroup sweeps a considerable amount of memory which is expected
950 to be accessed repeatedly by other cgroups, it may make sense to use
951 POSIX_FADV_DONTNEED to relinquish the ownership of memory areas
952 belonging to the affected files to ensure correct memory ownership.
957 The "io" controller regulates the distribution of IO resources. This
958 controller implements both weight based and absolute bandwidth or IOPS
959 limit distribution; however, weight based distribution is available
960 only if cfq-iosched is in use and neither scheme is available for
964 5-3-1. IO Interface Files
968 A read-only nested-keyed file which exists on non-root
971 Lines are keyed by $MAJ:$MIN device numbers and not ordered.
972 The following nested keys are defined.
976 rios Number of read IOs
977 wios Number of write IOs
979 An example read output follows.
981 8:16 rbytes=1459200 wbytes=314773504 rios=192 wios=353
982 8:0 rbytes=90430464 wbytes=299008000 rios=8950 wios=1252
986 A read-write flat-keyed file which exists on non-root cgroups.
987 The default is "default 100".
989 The first line is the default weight applied to devices
990 without specific override. The rest are overrides keyed by
991 $MAJ:$MIN device numbers and not ordered. The weights are in
992 the range [1, 10000] and specifies the relative amount IO time
993 the cgroup can use in relation to its siblings.
995 The default weight can be updated by writing either "default
996 $WEIGHT" or simply "$WEIGHT". Overrides can be set by writing
997 "$MAJ:$MIN $WEIGHT" and unset by writing "$MAJ:$MIN default".
999 An example read output follows.
1007 A read-write nested-keyed file which exists on non-root
1010 BPS and IOPS based IO limit. Lines are keyed by $MAJ:$MIN
1011 device numbers and not ordered. The following nested keys are
1014 rbps Max read bytes per second
1015 wbps Max write bytes per second
1016 riops Max read IO operations per second
1017 wiops Max write IO operations per second
1019 When writing, any number of nested key-value pairs can be
1020 specified in any order. "max" can be specified as the value
1021 to remove a specific limit. If the same key is specified
1022 multiple times, the outcome is undefined.
1024 BPS and IOPS are measured in each IO direction and IOs are
1025 delayed if limit is reached. Temporary bursts are allowed.
1027 Setting read limit at 2M BPS and write at 120 IOPS for 8:16.
1029 echo "8:16 rbps=2097152 wiops=120" > io.max
1031 Reading returns the following.
1033 8:16 rbps=2097152 wbps=max riops=max wiops=120
1035 Write IOPS limit can be removed by writing the following.
1037 echo "8:16 wiops=max" > io.max
1039 Reading now returns the following.
1041 8:16 rbps=2097152 wbps=max riops=max wiops=max
1046 Page cache is dirtied through buffered writes and shared mmaps and
1047 written asynchronously to the backing filesystem by the writeback
1048 mechanism. Writeback sits between the memory and IO domains and
1049 regulates the proportion of dirty memory by balancing dirtying and
1052 The io controller, in conjunction with the memory controller,
1053 implements control of page cache writeback IOs. The memory controller
1054 defines the memory domain that dirty memory ratio is calculated and
1055 maintained for and the io controller defines the io domain which
1056 writes out dirty pages for the memory domain. Both system-wide and
1057 per-cgroup dirty memory states are examined and the more restrictive
1058 of the two is enforced.
1060 cgroup writeback requires explicit support from the underlying
1061 filesystem. Currently, cgroup writeback is implemented on ext2, ext4
1062 and btrfs. On other filesystems, all writeback IOs are attributed to
1065 There are inherent differences in memory and writeback management
1066 which affects how cgroup ownership is tracked. Memory is tracked per
1067 page while writeback per inode. For the purpose of writeback, an
1068 inode is assigned to a cgroup and all IO requests to write dirty pages
1069 from the inode are attributed to that cgroup.
1071 As cgroup ownership for memory is tracked per page, there can be pages
1072 which are associated with different cgroups than the one the inode is
1073 associated with. These are called foreign pages. The writeback
1074 constantly keeps track of foreign pages and, if a particular foreign
1075 cgroup becomes the majority over a certain period of time, switches
1076 the ownership of the inode to that cgroup.
1078 While this model is enough for most use cases where a given inode is
1079 mostly dirtied by a single cgroup even when the main writing cgroup
1080 changes over time, use cases where multiple cgroups write to a single
1081 inode simultaneously are not supported well. In such circumstances, a
1082 significant portion of IOs are likely to be attributed incorrectly.
1083 As memory controller assigns page ownership on the first use and
1084 doesn't update it until the page is released, even if writeback
1085 strictly follows page ownership, multiple cgroups dirtying overlapping
1086 areas wouldn't work as expected. It's recommended to avoid such usage
1089 The sysctl knobs which affect writeback behavior are applied to cgroup
1090 writeback as follows.
1092 vm.dirty_background_ratio
1095 These ratios apply the same to cgroup writeback with the
1096 amount of available memory capped by limits imposed by the
1097 memory controller and system-wide clean memory.
1099 vm.dirty_background_bytes
1102 For cgroup writeback, this is calculated into ratio against
1103 total available memory and applied the same way as
1104 vm.dirty[_background]_ratio.
1107 P. Information on Kernel Programming
1109 This section contains kernel programming information in the areas
1110 where interacting with cgroup is necessary. cgroup core and
1111 controllers are not covered.
1114 P-1. Filesystem Support for Writeback
1116 A filesystem can support cgroup writeback by updating
1117 address_space_operations->writepage[s]() to annotate bio's using the
1118 following two functions.
1120 wbc_init_bio(@wbc, @bio)
1122 Should be called for each bio carrying writeback data and
1123 associates the bio with the inode's owner cgroup. Can be
1124 called anytime between bio allocation and submission.
1126 wbc_account_io(@wbc, @page, @bytes)
1128 Should be called for each data segment being written out.
1129 While this function doesn't care exactly when it's called
1130 during the writeback session, it's the easiest and most
1131 natural to call it as data segments are added to a bio.
1133 With writeback bio's annotated, cgroup support can be enabled per
1134 super_block by setting SB_I_CGROUPWB in ->s_iflags. This allows for
1135 selective disabling of cgroup writeback support which is helpful when
1136 certain filesystem features, e.g. journaled data mode, are
1139 wbc_init_bio() binds the specified bio to its cgroup. Depending on
1140 the configuration, the bio may be executed at a lower priority and if
1141 the writeback session is holding shared resources, e.g. a journal
1142 entry, may lead to priority inversion. There is no one easy solution
1143 for the problem. Filesystems can try to work around specific problem
1144 cases by skipping wbc_init_bio() or using bio_associate_blkcg()
1148 D. Deprecated v1 Core Features
1150 - Multiple hierarchies including named ones are not supported.
1152 - All mount options and remounting are not supported.
1154 - The "tasks" file is removed and "cgroup.procs" is not sorted.
1156 - "cgroup.clone_children" is removed.
1158 - /proc/cgroups is meaningless for v2. Use "cgroup.controllers" file
1159 at the root instead.
1162 R. Issues with v1 and Rationales for v2
1164 R-1. Multiple Hierarchies
1166 cgroup v1 allowed an arbitrary number of hierarchies and each
1167 hierarchy could host any number of controllers. While this seemed to
1168 provide a high level of flexibility, it wasn't useful in practice.
1170 For example, as there is only one instance of each controller, utility
1171 type controllers such as freezer which can be useful in all
1172 hierarchies could only be used in one. The issue is exacerbated by
1173 the fact that controllers couldn't be moved to another hierarchy once
1174 hierarchies were populated. Another issue was that all controllers
1175 bound to a hierarchy were forced to have exactly the same view of the
1176 hierarchy. It wasn't possible to vary the granularity depending on
1177 the specific controller.
1179 In practice, these issues heavily limited which controllers could be
1180 put on the same hierarchy and most configurations resorted to putting
1181 each controller on its own hierarchy. Only closely related ones, such
1182 as the cpu and cpuacct controllers, made sense to be put on the same
1183 hierarchy. This often meant that userland ended up managing multiple
1184 similar hierarchies repeating the same steps on each hierarchy
1185 whenever a hierarchy management operation was necessary.
1187 Furthermore, support for multiple hierarchies came at a steep cost.
1188 It greatly complicated cgroup core implementation but more importantly
1189 the support for multiple hierarchies restricted how cgroup could be
1190 used in general and what controllers was able to do.
1192 There was no limit on how many hierarchies there might be, which meant
1193 that a thread's cgroup membership couldn't be described in finite
1194 length. The key might contain any number of entries and was unlimited
1195 in length, which made it highly awkward to manipulate and led to
1196 addition of controllers which existed only to identify membership,
1197 which in turn exacerbated the original problem of proliferating number
1200 Also, as a controller couldn't have any expectation regarding the
1201 topologies of hierarchies other controllers might be on, each
1202 controller had to assume that all other controllers were attached to
1203 completely orthogonal hierarchies. This made it impossible, or at
1204 least very cumbersome, for controllers to cooperate with each other.
1206 In most use cases, putting controllers on hierarchies which are
1207 completely orthogonal to each other isn't necessary. What usually is
1208 called for is the ability to have differing levels of granularity
1209 depending on the specific controller. In other words, hierarchy may
1210 be collapsed from leaf towards root when viewed from specific
1211 controllers. For example, a given configuration might not care about
1212 how memory is distributed beyond a certain level while still wanting
1213 to control how CPU cycles are distributed.
1216 R-2. Thread Granularity
1218 cgroup v1 allowed threads of a process to belong to different cgroups.
1219 This didn't make sense for some controllers and those controllers
1220 ended up implementing different ways to ignore such situations but
1221 much more importantly it blurred the line between API exposed to
1222 individual applications and system management interface.
1224 Generally, in-process knowledge is available only to the process
1225 itself; thus, unlike service-level organization of processes,
1226 categorizing threads of a process requires active participation from
1227 the application which owns the target process.
1229 cgroup v1 had an ambiguously defined delegation model which got abused
1230 in combination with thread granularity. cgroups were delegated to
1231 individual applications so that they can create and manage their own
1232 sub-hierarchies and control resource distributions along them. This
1233 effectively raised cgroup to the status of a syscall-like API exposed
1236 First of all, cgroup has a fundamentally inadequate interface to be
1237 exposed this way. For a process to access its own knobs, it has to
1238 extract the path on the target hierarchy from /proc/self/cgroup,
1239 construct the path by appending the name of the knob to the path, open
1240 and then read and/or write to it. This is not only extremely clunky
1241 and unusual but also inherently racy. There is no conventional way to
1242 define transaction across the required steps and nothing can guarantee
1243 that the process would actually be operating on its own sub-hierarchy.
1245 cgroup controllers implemented a number of knobs which would never be
1246 accepted as public APIs because they were just adding control knobs to
1247 system-management pseudo filesystem. cgroup ended up with interface
1248 knobs which were not properly abstracted or refined and directly
1249 revealed kernel internal details. These knobs got exposed to
1250 individual applications through the ill-defined delegation mechanism
1251 effectively abusing cgroup as a shortcut to implementing public APIs
1252 without going through the required scrutiny.
1254 This was painful for both userland and kernel. Userland ended up with
1255 misbehaving and poorly abstracted interfaces and kernel exposing and
1256 locked into constructs inadvertently.
1259 R-3. Competition Between Inner Nodes and Threads
1261 cgroup v1 allowed threads to be in any cgroups which created an
1262 interesting problem where threads belonging to a parent cgroup and its
1263 children cgroups competed for resources. This was nasty as two
1264 different types of entities competed and there was no obvious way to
1265 settle it. Different controllers did different things.
1267 The cpu controller considered threads and cgroups as equivalents and
1268 mapped nice levels to cgroup weights. This worked for some cases but
1269 fell flat when children wanted to be allocated specific ratios of CPU
1270 cycles and the number of internal threads fluctuated - the ratios
1271 constantly changed as the number of competing entities fluctuated.
1272 There also were other issues. The mapping from nice level to weight
1273 wasn't obvious or universal, and there were various other knobs which
1274 simply weren't available for threads.
1276 The io controller implicitly created a hidden leaf node for each
1277 cgroup to host the threads. The hidden leaf had its own copies of all
1278 the knobs with "leaf_" prefixed. While this allowed equivalent
1279 control over internal threads, it was with serious drawbacks. It
1280 always added an extra layer of nesting which wouldn't be necessary
1281 otherwise, made the interface messy and significantly complicated the
1284 The memory controller didn't have a way to control what happened
1285 between internal tasks and child cgroups and the behavior was not
1286 clearly defined. There were attempts to add ad-hoc behaviors and
1287 knobs to tailor the behavior to specific workloads which would have
1288 led to problems extremely difficult to resolve in the long term.
1290 Multiple controllers struggled with internal tasks and came up with
1291 different ways to deal with it; unfortunately, all the approaches were
1292 severely flawed and, furthermore, the widely different behaviors
1293 made cgroup as a whole highly inconsistent.
1295 This clearly is a problem which needs to be addressed from cgroup core
1299 R-4. Other Interface Issues
1301 cgroup v1 grew without oversight and developed a large number of
1302 idiosyncrasies and inconsistencies. One issue on the cgroup core side
1303 was how an empty cgroup was notified - a userland helper binary was
1304 forked and executed for each event. The event delivery wasn't
1305 recursive or delegatable. The limitations of the mechanism also led
1306 to in-kernel event delivery filtering mechanism further complicating
1309 Controller interfaces were problematic too. An extreme example is
1310 controllers completely ignoring hierarchical organization and treating
1311 all cgroups as if they were all located directly under the root
1312 cgroup. Some controllers exposed a large amount of inconsistent
1313 implementation details to userland.
1315 There also was no consistency across controllers. When a new cgroup
1316 was created, some controllers defaulted to not imposing extra
1317 restrictions while others disallowed any resource usage until
1318 explicitly configured. Configuration knobs for the same type of
1319 control used widely differing naming schemes and formats. Statistics
1320 and information knobs were named arbitrarily and used different
1321 formats and units even in the same controller.
1323 cgroup v2 establishes common conventions where appropriate and updates
1324 controllers so that they expose minimal and consistent interfaces.
1327 R-5. Controller Issues and Remedies
1331 The original lower boundary, the soft limit, is defined as a limit
1332 that is per default unset. As a result, the set of cgroups that
1333 global reclaim prefers is opt-in, rather than opt-out. The costs for
1334 optimizing these mostly negative lookups are so high that the
1335 implementation, despite its enormous size, does not even provide the
1336 basic desirable behavior. First off, the soft limit has no
1337 hierarchical meaning. All configured groups are organized in a global
1338 rbtree and treated like equal peers, regardless where they are located
1339 in the hierarchy. This makes subtree delegation impossible. Second,
1340 the soft limit reclaim pass is so aggressive that it not just
1341 introduces high allocation latencies into the system, but also impacts
1342 system performance due to overreclaim, to the point where the feature
1343 becomes self-defeating.
1345 The memory.low boundary on the other hand is a top-down allocated
1346 reserve. A cgroup enjoys reclaim protection when it and all its
1347 ancestors are below their low boundaries, which makes delegation of
1348 subtrees possible. Secondly, new cgroups have no reserve per default
1349 and in the common case most cgroups are eligible for the preferred
1350 reclaim pass. This allows the new low boundary to be efficiently
1351 implemented with just a minor addition to the generic reclaim code,
1352 without the need for out-of-band data structures and reclaim passes.
1353 Because the generic reclaim code considers all cgroups except for the
1354 ones running low in the preferred first reclaim pass, overreclaim of
1355 individual groups is eliminated as well, resulting in much better
1356 overall workload performance.
1358 The original high boundary, the hard limit, is defined as a strict
1359 limit that can not budge, even if the OOM killer has to be called.
1360 But this generally goes against the goal of making the most out of the
1361 available memory. The memory consumption of workloads varies during
1362 runtime, and that requires users to overcommit. But doing that with a
1363 strict upper limit requires either a fairly accurate prediction of the
1364 working set size or adding slack to the limit. Since working set size
1365 estimation is hard and error prone, and getting it wrong results in
1366 OOM kills, most users tend to err on the side of a looser limit and
1367 end up wasting precious resources.
1369 The memory.high boundary on the other hand can be set much more
1370 conservatively. When hit, it throttles allocations by forcing them
1371 into direct reclaim to work off the excess, but it never invokes the
1372 OOM killer. As a result, a high boundary that is chosen too
1373 aggressively will not terminate the processes, but instead it will
1374 lead to gradual performance degradation. The user can monitor this
1375 and make corrections until the minimal memory footprint that still
1376 gives acceptable performance is found.
1378 In extreme cases, with many concurrent allocations and a complete
1379 breakdown of reclaim progress within the group, the high boundary can
1380 be exceeded. But even then it's mostly better to satisfy the
1381 allocation from the slack available in other groups or the rest of the
1382 system than killing the group. Otherwise, memory.max is there to
1383 limit this type of spillover and ultimately contain buggy or even
1384 malicious applications.
1386 The combined memory+swap accounting and limiting is replaced by real
1387 control over swap space.
1389 The main argument for a combined memory+swap facility in the original
1390 cgroup design was that global or parental pressure would always be
1391 able to swap all anonymous memory of a child group, regardless of the
1392 child's own (possibly untrusted) configuration. However, untrusted
1393 groups can sabotage swapping by other means - such as referencing its
1394 anonymous memory in a tight loop - and an admin can not assume full
1395 swappability when overcommitting untrusted jobs.
1397 For trusted jobs, on the other hand, a combined counter is not an
1398 intuitive userspace interface, and it flies in the face of the idea
1399 that cgroup controllers should account and limit specific physical
1400 resources. Swap space is a resource like all others in the system,
1401 and that's why unified hierarchy allows distributing it separately.