8 :Author: Tejun Heo <tj@kernel.org>
10 This is the authoritative documentation on the design, interface and
11 conventions of cgroup v2. It describes all userland-visible aspects
12 of cgroup including core and specific controller behaviors. All
13 future changes must be reflected in this document. Documentation for
14 v1 is available under :ref:`Documentation/admin-guide/cgroup-v1/index.rst <cgroup-v1>`.
23 2-2. Organizing Processes and Threads
26 2-3. [Un]populated Notification
27 2-4. Controlling Controllers
28 2-4-1. Enabling and Disabling
29 2-4-2. Top-down Constraint
30 2-4-3. No Internal Process Constraint
32 2-5-1. Model of Delegation
33 2-5-2. Delegation Containment
35 2-6-1. Organize Once and Control
36 2-6-2. Avoid Name Collisions
37 3. Resource Distribution Models
45 4-3. Core Interface Files
48 5-1-1. CPU Interface Files
50 5-2-1. Memory Interface Files
51 5-2-2. Usage Guidelines
52 5-2-3. Memory Ownership
54 5-3-1. IO Interface Files
57 5-3-3-1. How IO Latency Throttling Works
58 5-3-3-2. IO Latency Interface Files
61 5-4-1. PID Interface Files
63 5.5-1. Cpuset Interface Files
66 5-7-1. RDMA Interface Files
68 5.8-1. HugeTLB Interface Files
70 5.9-1 Miscellaneous cgroup Interface Files
71 5.9-2 Migration and Ownership
74 5-N. Non-normative information
75 5-N-1. CPU controller root cgroup process behaviour
76 5-N-2. IO controller root cgroup process behaviour
79 6-2. The Root and Views
80 6-3. Migration and setns(2)
81 6-4. Interaction with Other Namespaces
82 P. Information on Kernel Programming
83 P-1. Filesystem Support for Writeback
84 D. Deprecated v1 Core Features
85 R. Issues with v1 and Rationales for v2
86 R-1. Multiple Hierarchies
87 R-2. Thread Granularity
88 R-3. Competition Between Inner Nodes and Threads
89 R-4. Other Interface Issues
90 R-5. Controller Issues and Remedies
100 "cgroup" stands for "control group" and is never capitalized. The
101 singular form is used to designate the whole feature and also as a
102 qualifier as in "cgroup controllers". When explicitly referring to
103 multiple individual control groups, the plural form "cgroups" is used.
109 cgroup is a mechanism to organize processes hierarchically and
110 distribute system resources along the hierarchy in a controlled and
113 cgroup is largely composed of two parts - the core and controllers.
114 cgroup core is primarily responsible for hierarchically organizing
115 processes. A cgroup controller is usually responsible for
116 distributing a specific type of system resource along the hierarchy
117 although there are utility controllers which serve purposes other than
118 resource distribution.
120 cgroups form a tree structure and every process in the system belongs
121 to one and only one cgroup. All threads of a process belong to the
122 same cgroup. On creation, all processes are put in the cgroup that
123 the parent process belongs to at the time. A process can be migrated
124 to another cgroup. Migration of a process doesn't affect already
125 existing descendant processes.
127 Following certain structural constraints, controllers may be enabled or
128 disabled selectively on a cgroup. All controller behaviors are
129 hierarchical - if a controller is enabled on a cgroup, it affects all
130 processes which belong to the cgroups consisting the inclusive
131 sub-hierarchy of the cgroup. When a controller is enabled on a nested
132 cgroup, it always restricts the resource distribution further. The
133 restrictions set closer to the root in the hierarchy can not be
134 overridden from further away.
143 Unlike v1, cgroup v2 has only single hierarchy. The cgroup v2
144 hierarchy can be mounted with the following mount command::
146 # mount -t cgroup2 none $MOUNT_POINT
148 cgroup2 filesystem has the magic number 0x63677270 ("cgrp"). All
149 controllers which support v2 and are not bound to a v1 hierarchy are
150 automatically bound to the v2 hierarchy and show up at the root.
151 Controllers which are not in active use in the v2 hierarchy can be
152 bound to other hierarchies. This allows mixing v2 hierarchy with the
153 legacy v1 multiple hierarchies in a fully backward compatible way.
155 A controller can be moved across hierarchies only after the controller
156 is no longer referenced in its current hierarchy. Because per-cgroup
157 controller states are destroyed asynchronously and controllers may
158 have lingering references, a controller may not show up immediately on
159 the v2 hierarchy after the final umount of the previous hierarchy.
160 Similarly, a controller should be fully disabled to be moved out of
161 the unified hierarchy and it may take some time for the disabled
162 controller to become available for other hierarchies; furthermore, due
163 to inter-controller dependencies, other controllers may need to be
166 While useful for development and manual configurations, moving
167 controllers dynamically between the v2 and other hierarchies is
168 strongly discouraged for production use. It is recommended to decide
169 the hierarchies and controller associations before starting using the
170 controllers after system boot.
172 During transition to v2, system management software might still
173 automount the v1 cgroup filesystem and so hijack all controllers
174 during boot, before manual intervention is possible. To make testing
175 and experimenting easier, the kernel parameter cgroup_no_v1= allows
176 disabling controllers in v1 and make them always available in v2.
178 cgroup v2 currently supports the following mount options.
181 Consider cgroup namespaces as delegation boundaries. This
182 option is system wide and can only be set on mount or modified
183 through remount from the init namespace. The mount option is
184 ignored on non-init namespace mounts. Please refer to the
185 Delegation section for details.
188 Reduce the latencies of dynamic cgroup modifications such as
189 task migrations and controller on/offs at the cost of making
190 hot path operations such as forks and exits more expensive.
191 The static usage pattern of creating a cgroup, enabling
192 controllers, and then seeding it with CLONE_INTO_CGROUP is
193 not affected by this option.
195 memory_[no]localevents
196 Only populate memory.events with data for the current cgroup,
197 and not any subtrees. This is legacy behaviour, the default
198 behaviour without this option is to include subtree counts.
199 This option is system wide and can only be set on mount or
200 modified through remount from the init namespace. The mount
201 option is ignored on non-init namespace mounts.
203 memory_[no]recursiveprot
204 Recursively apply memory.min and memory.low protection to
205 entire subtrees, without requiring explicit downward
206 propagation into leaf cgroups. This allows protecting entire
207 subtrees from one another, while retaining free competition
208 within those subtrees. This should have been the default
209 behavior but is a mount-option to avoid regressing setups
210 relying on the original semantics (e.g. specifying bogusly
211 high 'bypass' protection values at higher tree levels).
214 Organizing Processes and Threads
215 --------------------------------
220 Initially, only the root cgroup exists to which all processes belong.
221 A child cgroup can be created by creating a sub-directory::
225 A given cgroup may have multiple child cgroups forming a tree
226 structure. Each cgroup has a read-writable interface file
227 "cgroup.procs". When read, it lists the PIDs of all processes which
228 belong to the cgroup one-per-line. The PIDs are not ordered and the
229 same PID may show up more than once if the process got moved to
230 another cgroup and then back or the PID got recycled while reading.
232 A process can be migrated into a cgroup by writing its PID to the
233 target cgroup's "cgroup.procs" file. Only one process can be migrated
234 on a single write(2) call. If a process is composed of multiple
235 threads, writing the PID of any thread migrates all threads of the
238 When a process forks a child process, the new process is born into the
239 cgroup that the forking process belongs to at the time of the
240 operation. After exit, a process stays associated with the cgroup
241 that it belonged to at the time of exit until it's reaped; however, a
242 zombie process does not appear in "cgroup.procs" and thus can't be
243 moved to another cgroup.
245 A cgroup which doesn't have any children or live processes can be
246 destroyed by removing the directory. Note that a cgroup which doesn't
247 have any children and is associated only with zombie processes is
248 considered empty and can be removed::
252 "/proc/$PID/cgroup" lists a process's cgroup membership. If legacy
253 cgroup is in use in the system, this file may contain multiple lines,
254 one for each hierarchy. The entry for cgroup v2 is always in the
257 # cat /proc/842/cgroup
259 0::/test-cgroup/test-cgroup-nested
261 If the process becomes a zombie and the cgroup it was associated with
262 is removed subsequently, " (deleted)" is appended to the path::
264 # cat /proc/842/cgroup
266 0::/test-cgroup/test-cgroup-nested (deleted)
272 cgroup v2 supports thread granularity for a subset of controllers to
273 support use cases requiring hierarchical resource distribution across
274 the threads of a group of processes. By default, all threads of a
275 process belong to the same cgroup, which also serves as the resource
276 domain to host resource consumptions which are not specific to a
277 process or thread. The thread mode allows threads to be spread across
278 a subtree while still maintaining the common resource domain for them.
280 Controllers which support thread mode are called threaded controllers.
281 The ones which don't are called domain controllers.
283 Marking a cgroup threaded makes it join the resource domain of its
284 parent as a threaded cgroup. The parent may be another threaded
285 cgroup whose resource domain is further up in the hierarchy. The root
286 of a threaded subtree, that is, the nearest ancestor which is not
287 threaded, is called threaded domain or thread root interchangeably and
288 serves as the resource domain for the entire subtree.
290 Inside a threaded subtree, threads of a process can be put in
291 different cgroups and are not subject to the no internal process
292 constraint - threaded controllers can be enabled on non-leaf cgroups
293 whether they have threads in them or not.
295 As the threaded domain cgroup hosts all the domain resource
296 consumptions of the subtree, it is considered to have internal
297 resource consumptions whether there are processes in it or not and
298 can't have populated child cgroups which aren't threaded. Because the
299 root cgroup is not subject to no internal process constraint, it can
300 serve both as a threaded domain and a parent to domain cgroups.
302 The current operation mode or type of the cgroup is shown in the
303 "cgroup.type" file which indicates whether the cgroup is a normal
304 domain, a domain which is serving as the domain of a threaded subtree,
305 or a threaded cgroup.
307 On creation, a cgroup is always a domain cgroup and can be made
308 threaded by writing "threaded" to the "cgroup.type" file. The
309 operation is single direction::
311 # echo threaded > cgroup.type
313 Once threaded, the cgroup can't be made a domain again. To enable the
314 thread mode, the following conditions must be met.
316 - As the cgroup will join the parent's resource domain. The parent
317 must either be a valid (threaded) domain or a threaded cgroup.
319 - When the parent is an unthreaded domain, it must not have any domain
320 controllers enabled or populated domain children. The root is
321 exempt from this requirement.
323 Topology-wise, a cgroup can be in an invalid state. Please consider
324 the following topology::
326 A (threaded domain) - B (threaded) - C (domain, just created)
328 C is created as a domain but isn't connected to a parent which can
329 host child domains. C can't be used until it is turned into a
330 threaded cgroup. "cgroup.type" file will report "domain (invalid)" in
331 these cases. Operations which fail due to invalid topology use
332 EOPNOTSUPP as the errno.
334 A domain cgroup is turned into a threaded domain when one of its child
335 cgroup becomes threaded or threaded controllers are enabled in the
336 "cgroup.subtree_control" file while there are processes in the cgroup.
337 A threaded domain reverts to a normal domain when the conditions
340 When read, "cgroup.threads" contains the list of the thread IDs of all
341 threads in the cgroup. Except that the operations are per-thread
342 instead of per-process, "cgroup.threads" has the same format and
343 behaves the same way as "cgroup.procs". While "cgroup.threads" can be
344 written to in any cgroup, as it can only move threads inside the same
345 threaded domain, its operations are confined inside each threaded
348 The threaded domain cgroup serves as the resource domain for the whole
349 subtree, and, while the threads can be scattered across the subtree,
350 all the processes are considered to be in the threaded domain cgroup.
351 "cgroup.procs" in a threaded domain cgroup contains the PIDs of all
352 processes in the subtree and is not readable in the subtree proper.
353 However, "cgroup.procs" can be written to from anywhere in the subtree
354 to migrate all threads of the matching process to the cgroup.
356 Only threaded controllers can be enabled in a threaded subtree. When
357 a threaded controller is enabled inside a threaded subtree, it only
358 accounts for and controls resource consumptions associated with the
359 threads in the cgroup and its descendants. All consumptions which
360 aren't tied to a specific thread belong to the threaded domain cgroup.
362 Because a threaded subtree is exempt from no internal process
363 constraint, a threaded controller must be able to handle competition
364 between threads in a non-leaf cgroup and its child cgroups. Each
365 threaded controller defines how such competitions are handled.
368 [Un]populated Notification
369 --------------------------
371 Each non-root cgroup has a "cgroup.events" file which contains
372 "populated" field indicating whether the cgroup's sub-hierarchy has
373 live processes in it. Its value is 0 if there is no live process in
374 the cgroup and its descendants; otherwise, 1. poll and [id]notify
375 events are triggered when the value changes. This can be used, for
376 example, to start a clean-up operation after all processes of a given
377 sub-hierarchy have exited. The populated state updates and
378 notifications are recursive. Consider the following sub-hierarchy
379 where the numbers in the parentheses represent the numbers of processes
385 A, B and C's "populated" fields would be 1 while D's 0. After the one
386 process in C exits, B and C's "populated" fields would flip to "0" and
387 file modified events will be generated on the "cgroup.events" files of
391 Controlling Controllers
392 -----------------------
394 Enabling and Disabling
395 ~~~~~~~~~~~~~~~~~~~~~~
397 Each cgroup has a "cgroup.controllers" file which lists all
398 controllers available for the cgroup to enable::
400 # cat cgroup.controllers
403 No controller is enabled by default. Controllers can be enabled and
404 disabled by writing to the "cgroup.subtree_control" file::
406 # echo "+cpu +memory -io" > cgroup.subtree_control
408 Only controllers which are listed in "cgroup.controllers" can be
409 enabled. When multiple operations are specified as above, either they
410 all succeed or fail. If multiple operations on the same controller
411 are specified, the last one is effective.
413 Enabling a controller in a cgroup indicates that the distribution of
414 the target resource across its immediate children will be controlled.
415 Consider the following sub-hierarchy. The enabled controllers are
416 listed in parentheses::
418 A(cpu,memory) - B(memory) - C()
421 As A has "cpu" and "memory" enabled, A will control the distribution
422 of CPU cycles and memory to its children, in this case, B. As B has
423 "memory" enabled but not "CPU", C and D will compete freely on CPU
424 cycles but their division of memory available to B will be controlled.
426 As a controller regulates the distribution of the target resource to
427 the cgroup's children, enabling it creates the controller's interface
428 files in the child cgroups. In the above example, enabling "cpu" on B
429 would create the "cpu." prefixed controller interface files in C and
430 D. Likewise, disabling "memory" from B would remove the "memory."
431 prefixed controller interface files from C and D. This means that the
432 controller interface files - anything which doesn't start with
433 "cgroup." are owned by the parent rather than the cgroup itself.
439 Resources are distributed top-down and a cgroup can further distribute
440 a resource only if the resource has been distributed to it from the
441 parent. This means that all non-root "cgroup.subtree_control" files
442 can only contain controllers which are enabled in the parent's
443 "cgroup.subtree_control" file. A controller can be enabled only if
444 the parent has the controller enabled and a controller can't be
445 disabled if one or more children have it enabled.
448 No Internal Process Constraint
449 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
451 Non-root cgroups can distribute domain resources to their children
452 only when they don't have any processes of their own. In other words,
453 only domain cgroups which don't contain any processes can have domain
454 controllers enabled in their "cgroup.subtree_control" files.
456 This guarantees that, when a domain controller is looking at the part
457 of the hierarchy which has it enabled, processes are always only on
458 the leaves. This rules out situations where child cgroups compete
459 against internal processes of the parent.
461 The root cgroup is exempt from this restriction. Root contains
462 processes and anonymous resource consumption which can't be associated
463 with any other cgroups and requires special treatment from most
464 controllers. How resource consumption in the root cgroup is governed
465 is up to each controller (for more information on this topic please
466 refer to the Non-normative information section in the Controllers
469 Note that the restriction doesn't get in the way if there is no
470 enabled controller in the cgroup's "cgroup.subtree_control". This is
471 important as otherwise it wouldn't be possible to create children of a
472 populated cgroup. To control resource distribution of a cgroup, the
473 cgroup must create children and transfer all its processes to the
474 children before enabling controllers in its "cgroup.subtree_control"
484 A cgroup can be delegated in two ways. First, to a less privileged
485 user by granting write access of the directory and its "cgroup.procs",
486 "cgroup.threads" and "cgroup.subtree_control" files to the user.
487 Second, if the "nsdelegate" mount option is set, automatically to a
488 cgroup namespace on namespace creation.
490 Because the resource control interface files in a given directory
491 control the distribution of the parent's resources, the delegatee
492 shouldn't be allowed to write to them. For the first method, this is
493 achieved by not granting access to these files. For the second, the
494 kernel rejects writes to all files other than "cgroup.procs" and
495 "cgroup.subtree_control" on a namespace root from inside the
498 The end results are equivalent for both delegation types. Once
499 delegated, the user can build sub-hierarchy under the directory,
500 organize processes inside it as it sees fit and further distribute the
501 resources it received from the parent. The limits and other settings
502 of all resource controllers are hierarchical and regardless of what
503 happens in the delegated sub-hierarchy, nothing can escape the
504 resource restrictions imposed by the parent.
506 Currently, cgroup doesn't impose any restrictions on the number of
507 cgroups in or nesting depth of a delegated sub-hierarchy; however,
508 this may be limited explicitly in the future.
511 Delegation Containment
512 ~~~~~~~~~~~~~~~~~~~~~~
514 A delegated sub-hierarchy is contained in the sense that processes
515 can't be moved into or out of the sub-hierarchy by the delegatee.
517 For delegations to a less privileged user, this is achieved by
518 requiring the following conditions for a process with a non-root euid
519 to migrate a target process into a cgroup by writing its PID to the
522 - The writer must have write access to the "cgroup.procs" file.
524 - The writer must have write access to the "cgroup.procs" file of the
525 common ancestor of the source and destination cgroups.
527 The above two constraints ensure that while a delegatee may migrate
528 processes around freely in the delegated sub-hierarchy it can't pull
529 in from or push out to outside the sub-hierarchy.
531 For an example, let's assume cgroups C0 and C1 have been delegated to
532 user U0 who created C00, C01 under C0 and C10 under C1 as follows and
533 all processes under C0 and C1 belong to U0::
535 ~~~~~~~~~~~~~ - C0 - C00
538 ~~~~~~~~~~~~~ - C1 - C10
540 Let's also say U0 wants to write the PID of a process which is
541 currently in C10 into "C00/cgroup.procs". U0 has write access to the
542 file; however, the common ancestor of the source cgroup C10 and the
543 destination cgroup C00 is above the points of delegation and U0 would
544 not have write access to its "cgroup.procs" files and thus the write
545 will be denied with -EACCES.
547 For delegations to namespaces, containment is achieved by requiring
548 that both the source and destination cgroups are reachable from the
549 namespace of the process which is attempting the migration. If either
550 is not reachable, the migration is rejected with -ENOENT.
556 Organize Once and Control
557 ~~~~~~~~~~~~~~~~~~~~~~~~~
559 Migrating a process across cgroups is a relatively expensive operation
560 and stateful resources such as memory are not moved together with the
561 process. This is an explicit design decision as there often exist
562 inherent trade-offs between migration and various hot paths in terms
563 of synchronization cost.
565 As such, migrating processes across cgroups frequently as a means to
566 apply different resource restrictions is discouraged. A workload
567 should be assigned to a cgroup according to the system's logical and
568 resource structure once on start-up. Dynamic adjustments to resource
569 distribution can be made by changing controller configuration through
573 Avoid Name Collisions
574 ~~~~~~~~~~~~~~~~~~~~~
576 Interface files for a cgroup and its children cgroups occupy the same
577 directory and it is possible to create children cgroups which collide
578 with interface files.
580 All cgroup core interface files are prefixed with "cgroup." and each
581 controller's interface files are prefixed with the controller name and
582 a dot. A controller's name is composed of lower case alphabets and
583 '_'s but never begins with an '_' so it can be used as the prefix
584 character for collision avoidance. Also, interface file names won't
585 start or end with terms which are often used in categorizing workloads
586 such as job, service, slice, unit or workload.
588 cgroup doesn't do anything to prevent name collisions and it's the
589 user's responsibility to avoid them.
592 Resource Distribution Models
593 ============================
595 cgroup controllers implement several resource distribution schemes
596 depending on the resource type and expected use cases. This section
597 describes major schemes in use along with their expected behaviors.
603 A parent's resource is distributed by adding up the weights of all
604 active children and giving each the fraction matching the ratio of its
605 weight against the sum. As only children which can make use of the
606 resource at the moment participate in the distribution, this is
607 work-conserving. Due to the dynamic nature, this model is usually
608 used for stateless resources.
610 All weights are in the range [1, 10000] with the default at 100. This
611 allows symmetric multiplicative biases in both directions at fine
612 enough granularity while staying in the intuitive range.
614 As long as the weight is in range, all configuration combinations are
615 valid and there is no reason to reject configuration changes or
618 "cpu.weight" proportionally distributes CPU cycles to active children
619 and is an example of this type.
625 A child can only consume upto the configured amount of the resource.
626 Limits can be over-committed - the sum of the limits of children can
627 exceed the amount of resource available to the parent.
629 Limits are in the range [0, max] and defaults to "max", which is noop.
631 As limits can be over-committed, all configuration combinations are
632 valid and there is no reason to reject configuration changes or
635 "io.max" limits the maximum BPS and/or IOPS that a cgroup can consume
636 on an IO device and is an example of this type.
642 A cgroup is protected upto the configured amount of the resource
643 as long as the usages of all its ancestors are under their
644 protected levels. Protections can be hard guarantees or best effort
645 soft boundaries. Protections can also be over-committed in which case
646 only upto the amount available to the parent is protected among
649 Protections are in the range [0, max] and defaults to 0, which is
652 As protections can be over-committed, all configuration combinations
653 are valid and there is no reason to reject configuration changes or
656 "memory.low" implements best-effort memory protection and is an
657 example of this type.
663 A cgroup is exclusively allocated a certain amount of a finite
664 resource. Allocations can't be over-committed - the sum of the
665 allocations of children can not exceed the amount of resource
666 available to the parent.
668 Allocations are in the range [0, max] and defaults to 0, which is no
671 As allocations can't be over-committed, some configuration
672 combinations are invalid and should be rejected. Also, if the
673 resource is mandatory for execution of processes, process migrations
676 "cpu.rt.max" hard-allocates realtime slices and is an example of this
686 All interface files should be in one of the following formats whenever
689 New-line separated values
690 (when only one value can be written at once)
696 Space separated values
697 (when read-only or multiple values can be written at once)
709 KEY0 SUB_KEY0=VAL00 SUB_KEY1=VAL01...
710 KEY1 SUB_KEY0=VAL10 SUB_KEY1=VAL11...
713 For a writable file, the format for writing should generally match
714 reading; however, controllers may allow omitting later fields or
715 implement restricted shortcuts for most common use cases.
717 For both flat and nested keyed files, only the values for a single key
718 can be written at a time. For nested keyed files, the sub key pairs
719 may be specified in any order and not all pairs have to be specified.
725 - Settings for a single feature should be contained in a single file.
727 - The root cgroup should be exempt from resource control and thus
728 shouldn't have resource control interface files.
730 - The default time unit is microseconds. If a different unit is ever
731 used, an explicit unit suffix must be present.
733 - A parts-per quantity should use a percentage decimal with at least
734 two digit fractional part - e.g. 13.40.
736 - If a controller implements weight based resource distribution, its
737 interface file should be named "weight" and have the range [1,
738 10000] with 100 as the default. The values are chosen to allow
739 enough and symmetric bias in both directions while keeping it
740 intuitive (the default is 100%).
742 - If a controller implements an absolute resource guarantee and/or
743 limit, the interface files should be named "min" and "max"
744 respectively. If a controller implements best effort resource
745 guarantee and/or limit, the interface files should be named "low"
746 and "high" respectively.
748 In the above four control files, the special token "max" should be
749 used to represent upward infinity for both reading and writing.
751 - If a setting has a configurable default value and keyed specific
752 overrides, the default entry should be keyed with "default" and
753 appear as the first entry in the file.
755 The default value can be updated by writing either "default $VAL" or
758 When writing to update a specific override, "default" can be used as
759 the value to indicate removal of the override. Override entries
760 with "default" as the value must not appear when read.
762 For example, a setting which is keyed by major:minor device numbers
763 with integer values may look like the following::
765 # cat cgroup-example-interface-file
769 The default value can be updated by::
771 # echo 125 > cgroup-example-interface-file
775 # echo "default 125" > cgroup-example-interface-file
777 An override can be set by::
779 # echo "8:16 170" > cgroup-example-interface-file
783 # echo "8:0 default" > cgroup-example-interface-file
784 # cat cgroup-example-interface-file
788 - For events which are not very high frequency, an interface file
789 "events" should be created which lists event key value pairs.
790 Whenever a notifiable event happens, file modified event should be
791 generated on the file.
797 All cgroup core files are prefixed with "cgroup."
800 A read-write single value file which exists on non-root
803 When read, it indicates the current type of the cgroup, which
804 can be one of the following values.
806 - "domain" : A normal valid domain cgroup.
808 - "domain threaded" : A threaded domain cgroup which is
809 serving as the root of a threaded subtree.
811 - "domain invalid" : A cgroup which is in an invalid state.
812 It can't be populated or have controllers enabled. It may
813 be allowed to become a threaded cgroup.
815 - "threaded" : A threaded cgroup which is a member of a
818 A cgroup can be turned into a threaded cgroup by writing
819 "threaded" to this file.
822 A read-write new-line separated values file which exists on
825 When read, it lists the PIDs of all processes which belong to
826 the cgroup one-per-line. The PIDs are not ordered and the
827 same PID may show up more than once if the process got moved
828 to another cgroup and then back or the PID got recycled while
831 A PID can be written to migrate the process associated with
832 the PID to the cgroup. The writer should match all of the
833 following conditions.
835 - It must have write access to the "cgroup.procs" file.
837 - It must have write access to the "cgroup.procs" file of the
838 common ancestor of the source and destination cgroups.
840 When delegating a sub-hierarchy, write access to this file
841 should be granted along with the containing directory.
843 In a threaded cgroup, reading this file fails with EOPNOTSUPP
844 as all the processes belong to the thread root. Writing is
845 supported and moves every thread of the process to the cgroup.
848 A read-write new-line separated values file which exists on
851 When read, it lists the TIDs of all threads which belong to
852 the cgroup one-per-line. The TIDs are not ordered and the
853 same TID may show up more than once if the thread got moved to
854 another cgroup and then back or the TID got recycled while
857 A TID can be written to migrate the thread associated with the
858 TID to the cgroup. The writer should match all of the
859 following conditions.
861 - It must have write access to the "cgroup.threads" file.
863 - The cgroup that the thread is currently in must be in the
864 same resource domain as the destination cgroup.
866 - It must have write access to the "cgroup.procs" file of the
867 common ancestor of the source and destination cgroups.
869 When delegating a sub-hierarchy, write access to this file
870 should be granted along with the containing directory.
873 A read-only space separated values file which exists on all
876 It shows space separated list of all controllers available to
877 the cgroup. The controllers are not ordered.
879 cgroup.subtree_control
880 A read-write space separated values file which exists on all
881 cgroups. Starts out empty.
883 When read, it shows space separated list of the controllers
884 which are enabled to control resource distribution from the
885 cgroup to its children.
887 Space separated list of controllers prefixed with '+' or '-'
888 can be written to enable or disable controllers. A controller
889 name prefixed with '+' enables the controller and '-'
890 disables. If a controller appears more than once on the list,
891 the last one is effective. When multiple enable and disable
892 operations are specified, either all succeed or all fail.
895 A read-only flat-keyed file which exists on non-root cgroups.
896 The following entries are defined. Unless specified
897 otherwise, a value change in this file generates a file
901 1 if the cgroup or its descendants contains any live
902 processes; otherwise, 0.
904 1 if the cgroup is frozen; otherwise, 0.
906 cgroup.max.descendants
907 A read-write single value files. The default is "max".
909 Maximum allowed number of descent cgroups.
910 If the actual number of descendants is equal or larger,
911 an attempt to create a new cgroup in the hierarchy will fail.
914 A read-write single value files. The default is "max".
916 Maximum allowed descent depth below the current cgroup.
917 If the actual descent depth is equal or larger,
918 an attempt to create a new child cgroup will fail.
921 A read-only flat-keyed file with the following entries:
924 Total number of visible descendant cgroups.
927 Total number of dying descendant cgroups. A cgroup becomes
928 dying after being deleted by a user. The cgroup will remain
929 in dying state for some time undefined time (which can depend
930 on system load) before being completely destroyed.
932 A process can't enter a dying cgroup under any circumstances,
933 a dying cgroup can't revive.
935 A dying cgroup can consume system resources not exceeding
936 limits, which were active at the moment of cgroup deletion.
939 A read-write single value file which exists on non-root cgroups.
940 Allowed values are "0" and "1". The default is "0".
942 Writing "1" to the file causes freezing of the cgroup and all
943 descendant cgroups. This means that all belonging processes will
944 be stopped and will not run until the cgroup will be explicitly
945 unfrozen. Freezing of the cgroup may take some time; when this action
946 is completed, the "frozen" value in the cgroup.events control file
947 will be updated to "1" and the corresponding notification will be
950 A cgroup can be frozen either by its own settings, or by settings
951 of any ancestor cgroups. If any of ancestor cgroups is frozen, the
952 cgroup will remain frozen.
954 Processes in the frozen cgroup can be killed by a fatal signal.
955 They also can enter and leave a frozen cgroup: either by an explicit
956 move by a user, or if freezing of the cgroup races with fork().
957 If a process is moved to a frozen cgroup, it stops. If a process is
958 moved out of a frozen cgroup, it becomes running.
960 Frozen status of a cgroup doesn't affect any cgroup tree operations:
961 it's possible to delete a frozen (and empty) cgroup, as well as
962 create new sub-cgroups.
965 A write-only single value file which exists in non-root cgroups.
966 The only allowed value is "1".
968 Writing "1" to the file causes the cgroup and all descendant cgroups to
969 be killed. This means that all processes located in the affected cgroup
970 tree will be killed via SIGKILL.
972 Killing a cgroup tree will deal with concurrent forks appropriately and
973 is protected against migrations.
975 In a threaded cgroup, writing this file fails with EOPNOTSUPP as
976 killing cgroups is a process directed operation, i.e. it affects
977 the whole thread-group.
987 The "cpu" controllers regulates distribution of CPU cycles. This
988 controller implements weight and absolute bandwidth limit models for
989 normal scheduling policy and absolute bandwidth allocation model for
990 realtime scheduling policy.
992 In all the above models, cycles distribution is defined only on a temporal
993 base and it does not account for the frequency at which tasks are executed.
994 The (optional) utilization clamping support allows to hint the schedutil
995 cpufreq governor about the minimum desired frequency which should always be
996 provided by a CPU, as well as the maximum desired frequency, which should not
997 be exceeded by a CPU.
999 WARNING: cgroup2 doesn't yet support control of realtime processes and
1000 the cpu controller can only be enabled when all RT processes are in
1001 the root cgroup. Be aware that system management software may already
1002 have placed RT processes into nonroot cgroups during the system boot
1003 process, and these processes may need to be moved to the root cgroup
1004 before the cpu controller can be enabled.
1010 All time durations are in microseconds.
1013 A read-only flat-keyed file.
1014 This file exists whether the controller is enabled or not.
1016 It always reports the following three stats:
1022 and the following three when the controller is enabled:
1031 A read-write single value file which exists on non-root
1032 cgroups. The default is "100".
1034 The weight in the range [1, 10000].
1037 A read-write single value file which exists on non-root
1038 cgroups. The default is "0".
1040 The nice value is in the range [-20, 19].
1042 This interface file is an alternative interface for
1043 "cpu.weight" and allows reading and setting weight using the
1044 same values used by nice(2). Because the range is smaller and
1045 granularity is coarser for the nice values, the read value is
1046 the closest approximation of the current weight.
1049 A read-write two value file which exists on non-root cgroups.
1050 The default is "max 100000".
1052 The maximum bandwidth limit. It's in the following format::
1056 which indicates that the group may consume upto $MAX in each
1057 $PERIOD duration. "max" for $MAX indicates no limit. If only
1058 one number is written, $MAX is updated.
1061 A read-write single value file which exists on non-root
1062 cgroups. The default is "0".
1064 The burst in the range [0, $MAX].
1067 A read-write nested-keyed file.
1069 Shows pressure stall information for CPU. See
1070 :ref:`Documentation/accounting/psi.rst <psi>` for details.
1073 A read-write single value file which exists on non-root cgroups.
1074 The default is "0", i.e. no utilization boosting.
1076 The requested minimum utilization (protection) as a percentage
1077 rational number, e.g. 12.34 for 12.34%.
1079 This interface allows reading and setting minimum utilization clamp
1080 values similar to the sched_setattr(2). This minimum utilization
1081 value is used to clamp the task specific minimum utilization clamp.
1083 The requested minimum utilization (protection) is always capped by
1084 the current value for the maximum utilization (limit), i.e.
1088 A read-write single value file which exists on non-root cgroups.
1089 The default is "max". i.e. no utilization capping
1091 The requested maximum utilization (limit) as a percentage rational
1092 number, e.g. 98.76 for 98.76%.
1094 This interface allows reading and setting maximum utilization clamp
1095 values similar to the sched_setattr(2). This maximum utilization
1096 value is used to clamp the task specific maximum utilization clamp.
1103 The "memory" controller regulates distribution of memory. Memory is
1104 stateful and implements both limit and protection models. Due to the
1105 intertwining between memory usage and reclaim pressure and the
1106 stateful nature of memory, the distribution model is relatively
1109 While not completely water-tight, all major memory usages by a given
1110 cgroup are tracked so that the total memory consumption can be
1111 accounted and controlled to a reasonable extent. Currently, the
1112 following types of memory usages are tracked.
1114 - Userland memory - page cache and anonymous memory.
1116 - Kernel data structures such as dentries and inodes.
1118 - TCP socket buffers.
1120 The above list may expand in the future for better coverage.
1123 Memory Interface Files
1124 ~~~~~~~~~~~~~~~~~~~~~~
1126 All memory amounts are in bytes. If a value which is not aligned to
1127 PAGE_SIZE is written, the value may be rounded up to the closest
1128 PAGE_SIZE multiple when read back.
1131 A read-only single value file which exists on non-root
1134 The total amount of memory currently being used by the cgroup
1135 and its descendants.
1138 A read-write single value file which exists on non-root
1139 cgroups. The default is "0".
1141 Hard memory protection. If the memory usage of a cgroup
1142 is within its effective min boundary, the cgroup's memory
1143 won't be reclaimed under any conditions. If there is no
1144 unprotected reclaimable memory available, OOM killer
1145 is invoked. Above the effective min boundary (or
1146 effective low boundary if it is higher), pages are reclaimed
1147 proportionally to the overage, reducing reclaim pressure for
1150 Effective min boundary is limited by memory.min values of
1151 all ancestor cgroups. If there is memory.min overcommitment
1152 (child cgroup or cgroups are requiring more protected memory
1153 than parent will allow), then each child cgroup will get
1154 the part of parent's protection proportional to its
1155 actual memory usage below memory.min.
1157 Putting more memory than generally available under this
1158 protection is discouraged and may lead to constant OOMs.
1160 If a memory cgroup is not populated with processes,
1161 its memory.min is ignored.
1164 A read-write single value file which exists on non-root
1165 cgroups. The default is "0".
1167 Best-effort memory protection. If the memory usage of a
1168 cgroup is within its effective low boundary, the cgroup's
1169 memory won't be reclaimed unless there is no reclaimable
1170 memory available in unprotected cgroups.
1171 Above the effective low boundary (or
1172 effective min boundary if it is higher), pages are reclaimed
1173 proportionally to the overage, reducing reclaim pressure for
1176 Effective low boundary is limited by memory.low values of
1177 all ancestor cgroups. If there is memory.low overcommitment
1178 (child cgroup or cgroups are requiring more protected memory
1179 than parent will allow), then each child cgroup will get
1180 the part of parent's protection proportional to its
1181 actual memory usage below memory.low.
1183 Putting more memory than generally available under this
1184 protection is discouraged.
1187 A read-write single value file which exists on non-root
1188 cgroups. The default is "max".
1190 Memory usage throttle limit. This is the main mechanism to
1191 control memory usage of a cgroup. If a cgroup's usage goes
1192 over the high boundary, the processes of the cgroup are
1193 throttled and put under heavy reclaim pressure.
1195 Going over the high limit never invokes the OOM killer and
1196 under extreme conditions the limit may be breached.
1199 A read-write single value file which exists on non-root
1200 cgroups. The default is "max".
1202 Memory usage hard limit. This is the final protection
1203 mechanism. If a cgroup's memory usage reaches this limit and
1204 can't be reduced, the OOM killer is invoked in the cgroup.
1205 Under certain circumstances, the usage may go over the limit
1208 In default configuration regular 0-order allocations always
1209 succeed unless OOM killer chooses current task as a victim.
1211 Some kinds of allocations don't invoke the OOM killer.
1212 Caller could retry them differently, return into userspace
1213 as -ENOMEM or silently ignore in cases like disk readahead.
1215 This is the ultimate protection mechanism. As long as the
1216 high limit is used and monitored properly, this limit's
1217 utility is limited to providing the final safety net.
1220 A write-only nested-keyed file which exists for all cgroups.
1222 This is a simple interface to trigger memory reclaim in the
1225 This file accepts a single key, the number of bytes to reclaim.
1226 No nested keys are currently supported.
1230 echo "1G" > memory.reclaim
1232 The interface can be later extended with nested keys to
1233 configure the reclaim behavior. For example, specify the
1234 type of memory to reclaim from (anon, file, ..).
1236 Please note that the kernel can over or under reclaim from
1237 the target cgroup. If less bytes are reclaimed than the
1238 specified amount, -EAGAIN is returned.
1241 A read-only single value file which exists on non-root
1244 The max memory usage recorded for the cgroup and its
1245 descendants since the creation of the cgroup.
1248 A read-write single value file which exists on non-root
1249 cgroups. The default value is "0".
1251 Determines whether the cgroup should be treated as
1252 an indivisible workload by the OOM killer. If set,
1253 all tasks belonging to the cgroup or to its descendants
1254 (if the memory cgroup is not a leaf cgroup) are killed
1255 together or not at all. This can be used to avoid
1256 partial kills to guarantee workload integrity.
1258 Tasks with the OOM protection (oom_score_adj set to -1000)
1259 are treated as an exception and are never killed.
1261 If the OOM killer is invoked in a cgroup, it's not going
1262 to kill any tasks outside of this cgroup, regardless
1263 memory.oom.group values of ancestor cgroups.
1266 A read-only flat-keyed file which exists on non-root cgroups.
1267 The following entries are defined. Unless specified
1268 otherwise, a value change in this file generates a file
1271 Note that all fields in this file are hierarchical and the
1272 file modified event can be generated due to an event down the
1273 hierarchy. For the local events at the cgroup level see
1274 memory.events.local.
1277 The number of times the cgroup is reclaimed due to
1278 high memory pressure even though its usage is under
1279 the low boundary. This usually indicates that the low
1280 boundary is over-committed.
1283 The number of times processes of the cgroup are
1284 throttled and routed to perform direct memory reclaim
1285 because the high memory boundary was exceeded. For a
1286 cgroup whose memory usage is capped by the high limit
1287 rather than global memory pressure, this event's
1288 occurrences are expected.
1291 The number of times the cgroup's memory usage was
1292 about to go over the max boundary. If direct reclaim
1293 fails to bring it down, the cgroup goes to OOM state.
1296 The number of time the cgroup's memory usage was
1297 reached the limit and allocation was about to fail.
1299 This event is not raised if the OOM killer is not
1300 considered as an option, e.g. for failed high-order
1301 allocations or if caller asked to not retry attempts.
1304 The number of processes belonging to this cgroup
1305 killed by any kind of OOM killer.
1308 The number of times a group OOM has occurred.
1311 Similar to memory.events but the fields in the file are local
1312 to the cgroup i.e. not hierarchical. The file modified event
1313 generated on this file reflects only the local events.
1316 A read-only flat-keyed file which exists on non-root cgroups.
1318 This breaks down the cgroup's memory footprint into different
1319 types of memory, type-specific details, and other information
1320 on the state and past events of the memory management system.
1322 All memory amounts are in bytes.
1324 The entries are ordered to be human readable, and new entries
1325 can show up in the middle. Don't rely on items remaining in a
1326 fixed position; use the keys to look up specific values!
1328 If the entry has no per-node counter (or not show in the
1329 memory.numa_stat). We use 'npn' (non-per-node) as the tag
1330 to indicate that it will not show in the memory.numa_stat.
1333 Amount of memory used in anonymous mappings such as
1334 brk(), sbrk(), and mmap(MAP_ANONYMOUS)
1337 Amount of memory used to cache filesystem data,
1338 including tmpfs and shared memory.
1341 Amount of total kernel memory, including
1342 (kernel_stack, pagetables, percpu, vmalloc, slab) in
1343 addition to other kernel memory use cases.
1346 Amount of memory allocated to kernel stacks.
1349 Amount of memory allocated for page tables.
1352 Amount of memory used for storing per-cpu kernel
1356 Amount of memory used in network transmission buffers
1359 Amount of memory used for vmap backed memory.
1362 Amount of cached filesystem data that is swap-backed,
1363 such as tmpfs, shm segments, shared anonymous mmap()s
1366 Amount of memory consumed by the zswap compression backend.
1369 Amount of application memory swapped out to zswap.
1372 Amount of cached filesystem data mapped with mmap()
1375 Amount of cached filesystem data that was modified but
1376 not yet written back to disk
1379 Amount of cached filesystem data that was modified and
1380 is currently being written back to disk
1383 Amount of swap cached in memory. The swapcache is accounted
1384 against both memory and swap usage.
1387 Amount of memory used in anonymous mappings backed by
1388 transparent hugepages
1391 Amount of cached filesystem data backed by transparent
1395 Amount of shm, tmpfs, shared anonymous mmap()s backed by
1396 transparent hugepages
1398 inactive_anon, active_anon, inactive_file, active_file, unevictable
1399 Amount of memory, swap-backed and filesystem-backed,
1400 on the internal memory management lists used by the
1401 page reclaim algorithm.
1403 As these represent internal list state (eg. shmem pages are on anon
1404 memory management lists), inactive_foo + active_foo may not be equal to
1405 the value for the foo counter, since the foo counter is type-based, not
1409 Part of "slab" that might be reclaimed, such as
1410 dentries and inodes.
1413 Part of "slab" that cannot be reclaimed on memory
1417 Amount of memory used for storing in-kernel data
1420 workingset_refault_anon
1421 Number of refaults of previously evicted anonymous pages.
1423 workingset_refault_file
1424 Number of refaults of previously evicted file pages.
1426 workingset_activate_anon
1427 Number of refaulted anonymous pages that were immediately
1430 workingset_activate_file
1431 Number of refaulted file pages that were immediately activated.
1433 workingset_restore_anon
1434 Number of restored anonymous pages which have been detected as
1435 an active workingset before they got reclaimed.
1437 workingset_restore_file
1438 Number of restored file pages which have been detected as an
1439 active workingset before they got reclaimed.
1441 workingset_nodereclaim
1442 Number of times a shadow node has been reclaimed
1445 Total number of page faults incurred
1448 Number of major page faults incurred
1451 Amount of scanned pages (in an active LRU list)
1454 Amount of scanned pages (in an inactive LRU list)
1457 Amount of reclaimed pages
1460 Amount of pages moved to the active LRU list
1463 Amount of pages moved to the inactive LRU list
1466 Amount of pages postponed to be freed under memory pressure
1469 Amount of reclaimed lazyfree pages
1471 thp_fault_alloc (npn)
1472 Number of transparent hugepages which were allocated to satisfy
1473 a page fault. This counter is not present when CONFIG_TRANSPARENT_HUGEPAGE
1476 thp_collapse_alloc (npn)
1477 Number of transparent hugepages which were allocated to allow
1478 collapsing an existing range of pages. This counter is not
1479 present when CONFIG_TRANSPARENT_HUGEPAGE is not set.
1482 A read-only nested-keyed file which exists on non-root cgroups.
1484 This breaks down the cgroup's memory footprint into different
1485 types of memory, type-specific details, and other information
1486 per node on the state of the memory management system.
1488 This is useful for providing visibility into the NUMA locality
1489 information within an memcg since the pages are allowed to be
1490 allocated from any physical node. One of the use case is evaluating
1491 application performance by combining this information with the
1492 application's CPU allocation.
1494 All memory amounts are in bytes.
1496 The output format of memory.numa_stat is::
1498 type N0=<bytes in node 0> N1=<bytes in node 1> ...
1500 The entries are ordered to be human readable, and new entries
1501 can show up in the middle. Don't rely on items remaining in a
1502 fixed position; use the keys to look up specific values!
1504 The entries can refer to the memory.stat.
1507 A read-only single value file which exists on non-root
1510 The total amount of swap currently being used by the cgroup
1511 and its descendants.
1514 A read-write single value file which exists on non-root
1515 cgroups. The default is "max".
1517 Swap usage throttle limit. If a cgroup's swap usage exceeds
1518 this limit, all its further allocations will be throttled to
1519 allow userspace to implement custom out-of-memory procedures.
1521 This limit marks a point of no return for the cgroup. It is NOT
1522 designed to manage the amount of swapping a workload does
1523 during regular operation. Compare to memory.swap.max, which
1524 prohibits swapping past a set amount, but lets the cgroup
1525 continue unimpeded as long as other memory can be reclaimed.
1527 Healthy workloads are not expected to reach this limit.
1530 A read-write single value file which exists on non-root
1531 cgroups. The default is "max".
1533 Swap usage hard limit. If a cgroup's swap usage reaches this
1534 limit, anonymous memory of the cgroup will not be swapped out.
1537 A read-only flat-keyed file which exists on non-root cgroups.
1538 The following entries are defined. Unless specified
1539 otherwise, a value change in this file generates a file
1543 The number of times the cgroup's swap usage was over
1547 The number of times the cgroup's swap usage was about
1548 to go over the max boundary and swap allocation
1552 The number of times swap allocation failed either
1553 because of running out of swap system-wide or max
1556 When reduced under the current usage, the existing swap
1557 entries are reclaimed gradually and the swap usage may stay
1558 higher than the limit for an extended period of time. This
1559 reduces the impact on the workload and memory management.
1561 memory.zswap.current
1562 A read-only single value file which exists on non-root
1565 The total amount of memory consumed by the zswap compression
1569 A read-write single value file which exists on non-root
1570 cgroups. The default is "max".
1572 Zswap usage hard limit. If a cgroup's zswap pool reaches this
1573 limit, it will refuse to take any more stores before existing
1574 entries fault back in or are written out to disk.
1577 A read-only nested-keyed file.
1579 Shows pressure stall information for memory. See
1580 :ref:`Documentation/accounting/psi.rst <psi>` for details.
1586 "memory.high" is the main mechanism to control memory usage.
1587 Over-committing on high limit (sum of high limits > available memory)
1588 and letting global memory pressure to distribute memory according to
1589 usage is a viable strategy.
1591 Because breach of the high limit doesn't trigger the OOM killer but
1592 throttles the offending cgroup, a management agent has ample
1593 opportunities to monitor and take appropriate actions such as granting
1594 more memory or terminating the workload.
1596 Determining whether a cgroup has enough memory is not trivial as
1597 memory usage doesn't indicate whether the workload can benefit from
1598 more memory. For example, a workload which writes data received from
1599 network to a file can use all available memory but can also operate as
1600 performant with a small amount of memory. A measure of memory
1601 pressure - how much the workload is being impacted due to lack of
1602 memory - is necessary to determine whether a workload needs more
1603 memory; unfortunately, memory pressure monitoring mechanism isn't
1610 A memory area is charged to the cgroup which instantiated it and stays
1611 charged to the cgroup until the area is released. Migrating a process
1612 to a different cgroup doesn't move the memory usages that it
1613 instantiated while in the previous cgroup to the new cgroup.
1615 A memory area may be used by processes belonging to different cgroups.
1616 To which cgroup the area will be charged is in-deterministic; however,
1617 over time, the memory area is likely to end up in a cgroup which has
1618 enough memory allowance to avoid high reclaim pressure.
1620 If a cgroup sweeps a considerable amount of memory which is expected
1621 to be accessed repeatedly by other cgroups, it may make sense to use
1622 POSIX_FADV_DONTNEED to relinquish the ownership of memory areas
1623 belonging to the affected files to ensure correct memory ownership.
1629 The "io" controller regulates the distribution of IO resources. This
1630 controller implements both weight based and absolute bandwidth or IOPS
1631 limit distribution; however, weight based distribution is available
1632 only if cfq-iosched is in use and neither scheme is available for
1640 A read-only nested-keyed file.
1642 Lines are keyed by $MAJ:$MIN device numbers and not ordered.
1643 The following nested keys are defined.
1645 ====== =====================
1647 wbytes Bytes written
1648 rios Number of read IOs
1649 wios Number of write IOs
1650 dbytes Bytes discarded
1651 dios Number of discard IOs
1652 ====== =====================
1654 An example read output follows::
1656 8:16 rbytes=1459200 wbytes=314773504 rios=192 wios=353 dbytes=0 dios=0
1657 8:0 rbytes=90430464 wbytes=299008000 rios=8950 wios=1252 dbytes=50331648 dios=3021
1660 A read-write nested-keyed file which exists only on the root
1663 This file configures the Quality of Service of the IO cost
1664 model based controller (CONFIG_BLK_CGROUP_IOCOST) which
1665 currently implements "io.weight" proportional control. Lines
1666 are keyed by $MAJ:$MIN device numbers and not ordered. The
1667 line for a given device is populated on the first write for
1668 the device on "io.cost.qos" or "io.cost.model". The following
1669 nested keys are defined.
1671 ====== =====================================
1672 enable Weight-based control enable
1673 ctrl "auto" or "user"
1674 rpct Read latency percentile [0, 100]
1675 rlat Read latency threshold
1676 wpct Write latency percentile [0, 100]
1677 wlat Write latency threshold
1678 min Minimum scaling percentage [1, 10000]
1679 max Maximum scaling percentage [1, 10000]
1680 ====== =====================================
1682 The controller is disabled by default and can be enabled by
1683 setting "enable" to 1. "rpct" and "wpct" parameters default
1684 to zero and the controller uses internal device saturation
1685 state to adjust the overall IO rate between "min" and "max".
1687 When a better control quality is needed, latency QoS
1688 parameters can be configured. For example::
1690 8:16 enable=1 ctrl=auto rpct=95.00 rlat=75000 wpct=95.00 wlat=150000 min=50.00 max=150.0
1692 shows that on sdb, the controller is enabled, will consider
1693 the device saturated if the 95th percentile of read completion
1694 latencies is above 75ms or write 150ms, and adjust the overall
1695 IO issue rate between 50% and 150% accordingly.
1697 The lower the saturation point, the better the latency QoS at
1698 the cost of aggregate bandwidth. The narrower the allowed
1699 adjustment range between "min" and "max", the more conformant
1700 to the cost model the IO behavior. Note that the IO issue
1701 base rate may be far off from 100% and setting "min" and "max"
1702 blindly can lead to a significant loss of device capacity or
1703 control quality. "min" and "max" are useful for regulating
1704 devices which show wide temporary behavior changes - e.g. a
1705 ssd which accepts writes at the line speed for a while and
1706 then completely stalls for multiple seconds.
1708 When "ctrl" is "auto", the parameters are controlled by the
1709 kernel and may change automatically. Setting "ctrl" to "user"
1710 or setting any of the percentile and latency parameters puts
1711 it into "user" mode and disables the automatic changes. The
1712 automatic mode can be restored by setting "ctrl" to "auto".
1715 A read-write nested-keyed file which exists only on the root
1718 This file configures the cost model of the IO cost model based
1719 controller (CONFIG_BLK_CGROUP_IOCOST) which currently
1720 implements "io.weight" proportional control. Lines are keyed
1721 by $MAJ:$MIN device numbers and not ordered. The line for a
1722 given device is populated on the first write for the device on
1723 "io.cost.qos" or "io.cost.model". The following nested keys
1726 ===== ================================
1727 ctrl "auto" or "user"
1728 model The cost model in use - "linear"
1729 ===== ================================
1731 When "ctrl" is "auto", the kernel may change all parameters
1732 dynamically. When "ctrl" is set to "user" or any other
1733 parameters are written to, "ctrl" become "user" and the
1734 automatic changes are disabled.
1736 When "model" is "linear", the following model parameters are
1739 ============= ========================================
1740 [r|w]bps The maximum sequential IO throughput
1741 [r|w]seqiops The maximum 4k sequential IOs per second
1742 [r|w]randiops The maximum 4k random IOs per second
1743 ============= ========================================
1745 From the above, the builtin linear model determines the base
1746 costs of a sequential and random IO and the cost coefficient
1747 for the IO size. While simple, this model can cover most
1748 common device classes acceptably.
1750 The IO cost model isn't expected to be accurate in absolute
1751 sense and is scaled to the device behavior dynamically.
1753 If needed, tools/cgroup/iocost_coef_gen.py can be used to
1754 generate device-specific coefficients.
1757 A read-write flat-keyed file which exists on non-root cgroups.
1758 The default is "default 100".
1760 The first line is the default weight applied to devices
1761 without specific override. The rest are overrides keyed by
1762 $MAJ:$MIN device numbers and not ordered. The weights are in
1763 the range [1, 10000] and specifies the relative amount IO time
1764 the cgroup can use in relation to its siblings.
1766 The default weight can be updated by writing either "default
1767 $WEIGHT" or simply "$WEIGHT". Overrides can be set by writing
1768 "$MAJ:$MIN $WEIGHT" and unset by writing "$MAJ:$MIN default".
1770 An example read output follows::
1777 A read-write nested-keyed file which exists on non-root
1780 BPS and IOPS based IO limit. Lines are keyed by $MAJ:$MIN
1781 device numbers and not ordered. The following nested keys are
1784 ===== ==================================
1785 rbps Max read bytes per second
1786 wbps Max write bytes per second
1787 riops Max read IO operations per second
1788 wiops Max write IO operations per second
1789 ===== ==================================
1791 When writing, any number of nested key-value pairs can be
1792 specified in any order. "max" can be specified as the value
1793 to remove a specific limit. If the same key is specified
1794 multiple times, the outcome is undefined.
1796 BPS and IOPS are measured in each IO direction and IOs are
1797 delayed if limit is reached. Temporary bursts are allowed.
1799 Setting read limit at 2M BPS and write at 120 IOPS for 8:16::
1801 echo "8:16 rbps=2097152 wiops=120" > io.max
1803 Reading returns the following::
1805 8:16 rbps=2097152 wbps=max riops=max wiops=120
1807 Write IOPS limit can be removed by writing the following::
1809 echo "8:16 wiops=max" > io.max
1811 Reading now returns the following::
1813 8:16 rbps=2097152 wbps=max riops=max wiops=max
1816 A read-only nested-keyed file.
1818 Shows pressure stall information for IO. See
1819 :ref:`Documentation/accounting/psi.rst <psi>` for details.
1825 Page cache is dirtied through buffered writes and shared mmaps and
1826 written asynchronously to the backing filesystem by the writeback
1827 mechanism. Writeback sits between the memory and IO domains and
1828 regulates the proportion of dirty memory by balancing dirtying and
1831 The io controller, in conjunction with the memory controller,
1832 implements control of page cache writeback IOs. The memory controller
1833 defines the memory domain that dirty memory ratio is calculated and
1834 maintained for and the io controller defines the io domain which
1835 writes out dirty pages for the memory domain. Both system-wide and
1836 per-cgroup dirty memory states are examined and the more restrictive
1837 of the two is enforced.
1839 cgroup writeback requires explicit support from the underlying
1840 filesystem. Currently, cgroup writeback is implemented on ext2, ext4,
1841 btrfs, f2fs, and xfs. On other filesystems, all writeback IOs are
1842 attributed to the root cgroup.
1844 There are inherent differences in memory and writeback management
1845 which affects how cgroup ownership is tracked. Memory is tracked per
1846 page while writeback per inode. For the purpose of writeback, an
1847 inode is assigned to a cgroup and all IO requests to write dirty pages
1848 from the inode are attributed to that cgroup.
1850 As cgroup ownership for memory is tracked per page, there can be pages
1851 which are associated with different cgroups than the one the inode is
1852 associated with. These are called foreign pages. The writeback
1853 constantly keeps track of foreign pages and, if a particular foreign
1854 cgroup becomes the majority over a certain period of time, switches
1855 the ownership of the inode to that cgroup.
1857 While this model is enough for most use cases where a given inode is
1858 mostly dirtied by a single cgroup even when the main writing cgroup
1859 changes over time, use cases where multiple cgroups write to a single
1860 inode simultaneously are not supported well. In such circumstances, a
1861 significant portion of IOs are likely to be attributed incorrectly.
1862 As memory controller assigns page ownership on the first use and
1863 doesn't update it until the page is released, even if writeback
1864 strictly follows page ownership, multiple cgroups dirtying overlapping
1865 areas wouldn't work as expected. It's recommended to avoid such usage
1868 The sysctl knobs which affect writeback behavior are applied to cgroup
1869 writeback as follows.
1871 vm.dirty_background_ratio, vm.dirty_ratio
1872 These ratios apply the same to cgroup writeback with the
1873 amount of available memory capped by limits imposed by the
1874 memory controller and system-wide clean memory.
1876 vm.dirty_background_bytes, vm.dirty_bytes
1877 For cgroup writeback, this is calculated into ratio against
1878 total available memory and applied the same way as
1879 vm.dirty[_background]_ratio.
1885 This is a cgroup v2 controller for IO workload protection. You provide a group
1886 with a latency target, and if the average latency exceeds that target the
1887 controller will throttle any peers that have a lower latency target than the
1890 The limits are only applied at the peer level in the hierarchy. This means that
1891 in the diagram below, only groups A, B, and C will influence each other, and
1892 groups D and F will influence each other. Group G will influence nobody::
1901 So the ideal way to configure this is to set io.latency in groups A, B, and C.
1902 Generally you do not want to set a value lower than the latency your device
1903 supports. Experiment to find the value that works best for your workload.
1904 Start at higher than the expected latency for your device and watch the
1905 avg_lat value in io.stat for your workload group to get an idea of the
1906 latency you see during normal operation. Use the avg_lat value as a basis for
1907 your real setting, setting at 10-15% higher than the value in io.stat.
1909 How IO Latency Throttling Works
1910 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
1912 io.latency is work conserving; so as long as everybody is meeting their latency
1913 target the controller doesn't do anything. Once a group starts missing its
1914 target it begins throttling any peer group that has a higher target than itself.
1915 This throttling takes 2 forms:
1917 - Queue depth throttling. This is the number of outstanding IO's a group is
1918 allowed to have. We will clamp down relatively quickly, starting at no limit
1919 and going all the way down to 1 IO at a time.
1921 - Artificial delay induction. There are certain types of IO that cannot be
1922 throttled without possibly adversely affecting higher priority groups. This
1923 includes swapping and metadata IO. These types of IO are allowed to occur
1924 normally, however they are "charged" to the originating group. If the
1925 originating group is being throttled you will see the use_delay and delay
1926 fields in io.stat increase. The delay value is how many microseconds that are
1927 being added to any process that runs in this group. Because this number can
1928 grow quite large if there is a lot of swapping or metadata IO occurring we
1929 limit the individual delay events to 1 second at a time.
1931 Once the victimized group starts meeting its latency target again it will start
1932 unthrottling any peer groups that were throttled previously. If the victimized
1933 group simply stops doing IO the global counter will unthrottle appropriately.
1935 IO Latency Interface Files
1936 ~~~~~~~~~~~~~~~~~~~~~~~~~~
1939 This takes a similar format as the other controllers.
1941 "MAJOR:MINOR target=<target time in microseconds>"
1944 If the controller is enabled you will see extra stats in io.stat in
1945 addition to the normal ones.
1948 This is the current queue depth for the group.
1951 This is an exponential moving average with a decay rate of 1/exp
1952 bound by the sampling interval. The decay rate interval can be
1953 calculated by multiplying the win value in io.stat by the
1954 corresponding number of samples based on the win value.
1957 The sampling window size in milliseconds. This is the minimum
1958 duration of time between evaluation events. Windows only elapse
1959 with IO activity. Idle periods extend the most recent window.
1964 A single attribute controls the behavior of the I/O priority cgroup policy,
1965 namely the blkio.prio.class attribute. The following values are accepted for
1969 Do not modify the I/O priority class.
1972 For requests that do not have an I/O priority class (NONE),
1973 change the I/O priority class into RT. Do not modify
1974 the I/O priority class of other requests.
1977 For requests that do not have an I/O priority class or that have I/O
1978 priority class RT, change it into BE. Do not modify the I/O priority
1979 class of requests that have priority class IDLE.
1982 Change the I/O priority class of all requests into IDLE, the lowest
1985 The following numerical values are associated with the I/O priority policies:
1997 The numerical value that corresponds to each I/O priority class is as follows:
1999 +-------------------------------+---+
2000 | IOPRIO_CLASS_NONE | 0 |
2001 +-------------------------------+---+
2002 | IOPRIO_CLASS_RT (real-time) | 1 |
2003 +-------------------------------+---+
2004 | IOPRIO_CLASS_BE (best effort) | 2 |
2005 +-------------------------------+---+
2006 | IOPRIO_CLASS_IDLE | 3 |
2007 +-------------------------------+---+
2009 The algorithm to set the I/O priority class for a request is as follows:
2011 - Translate the I/O priority class policy into a number.
2012 - Change the request I/O priority class into the maximum of the I/O priority
2013 class policy number and the numerical I/O priority class.
2018 The process number controller is used to allow a cgroup to stop any
2019 new tasks from being fork()'d or clone()'d after a specified limit is
2022 The number of tasks in a cgroup can be exhausted in ways which other
2023 controllers cannot prevent, thus warranting its own controller. For
2024 example, a fork bomb is likely to exhaust the number of tasks before
2025 hitting memory restrictions.
2027 Note that PIDs used in this controller refer to TIDs, process IDs as
2035 A read-write single value file which exists on non-root
2036 cgroups. The default is "max".
2038 Hard limit of number of processes.
2041 A read-only single value file which exists on all cgroups.
2043 The number of processes currently in the cgroup and its
2046 Organisational operations are not blocked by cgroup policies, so it is
2047 possible to have pids.current > pids.max. This can be done by either
2048 setting the limit to be smaller than pids.current, or attaching enough
2049 processes to the cgroup such that pids.current is larger than
2050 pids.max. However, it is not possible to violate a cgroup PID policy
2051 through fork() or clone(). These will return -EAGAIN if the creation
2052 of a new process would cause a cgroup policy to be violated.
2058 The "cpuset" controller provides a mechanism for constraining
2059 the CPU and memory node placement of tasks to only the resources
2060 specified in the cpuset interface files in a task's current cgroup.
2061 This is especially valuable on large NUMA systems where placing jobs
2062 on properly sized subsets of the systems with careful processor and
2063 memory placement to reduce cross-node memory access and contention
2064 can improve overall system performance.
2066 The "cpuset" controller is hierarchical. That means the controller
2067 cannot use CPUs or memory nodes not allowed in its parent.
2070 Cpuset Interface Files
2071 ~~~~~~~~~~~~~~~~~~~~~~
2074 A read-write multiple values file which exists on non-root
2075 cpuset-enabled cgroups.
2077 It lists the requested CPUs to be used by tasks within this
2078 cgroup. The actual list of CPUs to be granted, however, is
2079 subjected to constraints imposed by its parent and can differ
2080 from the requested CPUs.
2082 The CPU numbers are comma-separated numbers or ranges.
2088 An empty value indicates that the cgroup is using the same
2089 setting as the nearest cgroup ancestor with a non-empty
2090 "cpuset.cpus" or all the available CPUs if none is found.
2092 The value of "cpuset.cpus" stays constant until the next update
2093 and won't be affected by any CPU hotplug events.
2095 cpuset.cpus.effective
2096 A read-only multiple values file which exists on all
2097 cpuset-enabled cgroups.
2099 It lists the onlined CPUs that are actually granted to this
2100 cgroup by its parent. These CPUs are allowed to be used by
2101 tasks within the current cgroup.
2103 If "cpuset.cpus" is empty, the "cpuset.cpus.effective" file shows
2104 all the CPUs from the parent cgroup that can be available to
2105 be used by this cgroup. Otherwise, it should be a subset of
2106 "cpuset.cpus" unless none of the CPUs listed in "cpuset.cpus"
2107 can be granted. In this case, it will be treated just like an
2108 empty "cpuset.cpus".
2110 Its value will be affected by CPU hotplug events.
2113 A read-write multiple values file which exists on non-root
2114 cpuset-enabled cgroups.
2116 It lists the requested memory nodes to be used by tasks within
2117 this cgroup. The actual list of memory nodes granted, however,
2118 is subjected to constraints imposed by its parent and can differ
2119 from the requested memory nodes.
2121 The memory node numbers are comma-separated numbers or ranges.
2127 An empty value indicates that the cgroup is using the same
2128 setting as the nearest cgroup ancestor with a non-empty
2129 "cpuset.mems" or all the available memory nodes if none
2132 The value of "cpuset.mems" stays constant until the next update
2133 and won't be affected by any memory nodes hotplug events.
2135 Setting a non-empty value to "cpuset.mems" causes memory of
2136 tasks within the cgroup to be migrated to the designated nodes if
2137 they are currently using memory outside of the designated nodes.
2139 There is a cost for this memory migration. The migration
2140 may not be complete and some memory pages may be left behind.
2141 So it is recommended that "cpuset.mems" should be set properly
2142 before spawning new tasks into the cpuset. Even if there is
2143 a need to change "cpuset.mems" with active tasks, it shouldn't
2146 cpuset.mems.effective
2147 A read-only multiple values file which exists on all
2148 cpuset-enabled cgroups.
2150 It lists the onlined memory nodes that are actually granted to
2151 this cgroup by its parent. These memory nodes are allowed to
2152 be used by tasks within the current cgroup.
2154 If "cpuset.mems" is empty, it shows all the memory nodes from the
2155 parent cgroup that will be available to be used by this cgroup.
2156 Otherwise, it should be a subset of "cpuset.mems" unless none of
2157 the memory nodes listed in "cpuset.mems" can be granted. In this
2158 case, it will be treated just like an empty "cpuset.mems".
2160 Its value will be affected by memory nodes hotplug events.
2162 cpuset.cpus.partition
2163 A read-write single value file which exists on non-root
2164 cpuset-enabled cgroups. This flag is owned by the parent cgroup
2165 and is not delegatable.
2167 It accepts only the following input values when written to.
2169 ======== ================================
2170 "root" a partition root
2171 "member" a non-root member of a partition
2172 ======== ================================
2174 When set to be a partition root, the current cgroup is the
2175 root of a new partition or scheduling domain that comprises
2176 itself and all its descendants except those that are separate
2177 partition roots themselves and their descendants. The root
2178 cgroup is always a partition root.
2180 There are constraints on where a partition root can be set.
2181 It can only be set in a cgroup if all the following conditions
2184 1) The "cpuset.cpus" is not empty and the list of CPUs are
2185 exclusive, i.e. they are not shared by any of its siblings.
2186 2) The parent cgroup is a partition root.
2187 3) The "cpuset.cpus" is also a proper subset of the parent's
2188 "cpuset.cpus.effective".
2189 4) There is no child cgroups with cpuset enabled. This is for
2190 eliminating corner cases that have to be handled if such a
2191 condition is allowed.
2193 Setting it to partition root will take the CPUs away from the
2194 effective CPUs of the parent cgroup. Once it is set, this
2195 file cannot be reverted back to "member" if there are any child
2196 cgroups with cpuset enabled.
2198 A parent partition cannot distribute all its CPUs to its
2199 child partitions. There must be at least one cpu left in the
2202 Once becoming a partition root, changes to "cpuset.cpus" is
2203 generally allowed as long as the first condition above is true,
2204 the change will not take away all the CPUs from the parent
2205 partition and the new "cpuset.cpus" value is a superset of its
2206 children's "cpuset.cpus" values.
2208 Sometimes, external factors like changes to ancestors'
2209 "cpuset.cpus" or cpu hotplug can cause the state of the partition
2210 root to change. On read, the "cpuset.sched.partition" file
2211 can show the following values.
2213 ============== ==============================
2214 "member" Non-root member of a partition
2215 "root" Partition root
2216 "root invalid" Invalid partition root
2217 ============== ==============================
2219 It is a partition root if the first 2 partition root conditions
2220 above are true and at least one CPU from "cpuset.cpus" is
2221 granted by the parent cgroup.
2223 A partition root can become invalid if none of CPUs requested
2224 in "cpuset.cpus" can be granted by the parent cgroup or the
2225 parent cgroup is no longer a partition root itself. In this
2226 case, it is not a real partition even though the restriction
2227 of the first partition root condition above will still apply.
2228 The cpu affinity of all the tasks in the cgroup will then be
2229 associated with CPUs in the nearest ancestor partition.
2231 An invalid partition root can be transitioned back to a
2232 real partition root if at least one of the requested CPUs
2233 can now be granted by its parent. In this case, the cpu
2234 affinity of all the tasks in the formerly invalid partition
2235 will be associated to the CPUs of the newly formed partition.
2236 Changing the partition state of an invalid partition root to
2237 "member" is always allowed even if child cpusets are present.
2243 Device controller manages access to device files. It includes both
2244 creation of new device files (using mknod), and access to the
2245 existing device files.
2247 Cgroup v2 device controller has no interface files and is implemented
2248 on top of cgroup BPF. To control access to device files, a user may
2249 create bpf programs of type BPF_PROG_TYPE_CGROUP_DEVICE and attach
2250 them to cgroups with BPF_CGROUP_DEVICE flag. On an attempt to access a
2251 device file, corresponding BPF programs will be executed, and depending
2252 on the return value the attempt will succeed or fail with -EPERM.
2254 A BPF_PROG_TYPE_CGROUP_DEVICE program takes a pointer to the
2255 bpf_cgroup_dev_ctx structure, which describes the device access attempt:
2256 access type (mknod/read/write) and device (type, major and minor numbers).
2257 If the program returns 0, the attempt fails with -EPERM, otherwise it
2260 An example of BPF_PROG_TYPE_CGROUP_DEVICE program may be found in
2261 tools/testing/selftests/bpf/progs/dev_cgroup.c in the kernel source tree.
2267 The "rdma" controller regulates the distribution and accounting of
2270 RDMA Interface Files
2271 ~~~~~~~~~~~~~~~~~~~~
2274 A readwrite nested-keyed file that exists for all the cgroups
2275 except root that describes current configured resource limit
2276 for a RDMA/IB device.
2278 Lines are keyed by device name and are not ordered.
2279 Each line contains space separated resource name and its configured
2280 limit that can be distributed.
2282 The following nested keys are defined.
2284 ========== =============================
2285 hca_handle Maximum number of HCA Handles
2286 hca_object Maximum number of HCA Objects
2287 ========== =============================
2289 An example for mlx4 and ocrdma device follows::
2291 mlx4_0 hca_handle=2 hca_object=2000
2292 ocrdma1 hca_handle=3 hca_object=max
2295 A read-only file that describes current resource usage.
2296 It exists for all the cgroup except root.
2298 An example for mlx4 and ocrdma device follows::
2300 mlx4_0 hca_handle=1 hca_object=20
2301 ocrdma1 hca_handle=1 hca_object=23
2306 The HugeTLB controller allows to limit the HugeTLB usage per control group and
2307 enforces the controller limit during page fault.
2309 HugeTLB Interface Files
2310 ~~~~~~~~~~~~~~~~~~~~~~~
2312 hugetlb.<hugepagesize>.current
2313 Show current usage for "hugepagesize" hugetlb. It exists for all
2314 the cgroup except root.
2316 hugetlb.<hugepagesize>.max
2317 Set/show the hard limit of "hugepagesize" hugetlb usage.
2318 The default value is "max". It exists for all the cgroup except root.
2320 hugetlb.<hugepagesize>.events
2321 A read-only flat-keyed file which exists on non-root cgroups.
2324 The number of allocation failure due to HugeTLB limit
2326 hugetlb.<hugepagesize>.events.local
2327 Similar to hugetlb.<hugepagesize>.events but the fields in the file
2328 are local to the cgroup i.e. not hierarchical. The file modified event
2329 generated on this file reflects only the local events.
2331 hugetlb.<hugepagesize>.numa_stat
2332 Similar to memory.numa_stat, it shows the numa information of the
2333 hugetlb pages of <hugepagesize> in this cgroup. Only active in
2334 use hugetlb pages are included. The per-node values are in bytes.
2339 The Miscellaneous cgroup provides the resource limiting and tracking
2340 mechanism for the scalar resources which cannot be abstracted like the other
2341 cgroup resources. Controller is enabled by the CONFIG_CGROUP_MISC config
2344 A resource can be added to the controller via enum misc_res_type{} in the
2345 include/linux/misc_cgroup.h file and the corresponding name via misc_res_name[]
2346 in the kernel/cgroup/misc.c file. Provider of the resource must set its
2347 capacity prior to using the resource by calling misc_cg_set_capacity().
2349 Once a capacity is set then the resource usage can be updated using charge and
2350 uncharge APIs. All of the APIs to interact with misc controller are in
2351 include/linux/misc_cgroup.h.
2353 Misc Interface Files
2354 ~~~~~~~~~~~~~~~~~~~~
2356 Miscellaneous controller provides 3 interface files. If two misc resources (res_a and res_b) are registered then:
2359 A read-only flat-keyed file shown only in the root cgroup. It shows
2360 miscellaneous scalar resources available on the platform along with
2368 A read-only flat-keyed file shown in the non-root cgroups. It shows
2369 the current usage of the resources in the cgroup and its children.::
2376 A read-write flat-keyed file shown in the non root cgroups. Allowed
2377 maximum usage of the resources in the cgroup and its children.::
2383 Limit can be set by::
2385 # echo res_a 1 > misc.max
2387 Limit can be set to max by::
2389 # echo res_a max > misc.max
2391 Limits can be set higher than the capacity value in the misc.capacity
2395 A read-only flat-keyed file which exists on non-root cgroups. The
2396 following entries are defined. Unless specified otherwise, a value
2397 change in this file generates a file modified event. All fields in
2398 this file are hierarchical.
2401 The number of times the cgroup's resource usage was
2402 about to go over the max boundary.
2404 Migration and Ownership
2405 ~~~~~~~~~~~~~~~~~~~~~~~
2407 A miscellaneous scalar resource is charged to the cgroup in which it is used
2408 first, and stays charged to that cgroup until that resource is freed. Migrating
2409 a process to a different cgroup does not move the charge to the destination
2410 cgroup where the process has moved.
2418 perf_event controller, if not mounted on a legacy hierarchy, is
2419 automatically enabled on the v2 hierarchy so that perf events can
2420 always be filtered by cgroup v2 path. The controller can still be
2421 moved to a legacy hierarchy after v2 hierarchy is populated.
2424 Non-normative information
2425 -------------------------
2427 This section contains information that isn't considered to be a part of
2428 the stable kernel API and so is subject to change.
2431 CPU controller root cgroup process behaviour
2432 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2434 When distributing CPU cycles in the root cgroup each thread in this
2435 cgroup is treated as if it was hosted in a separate child cgroup of the
2436 root cgroup. This child cgroup weight is dependent on its thread nice
2439 For details of this mapping see sched_prio_to_weight array in
2440 kernel/sched/core.c file (values from this array should be scaled
2441 appropriately so the neutral - nice 0 - value is 100 instead of 1024).
2444 IO controller root cgroup process behaviour
2445 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2447 Root cgroup processes are hosted in an implicit leaf child node.
2448 When distributing IO resources this implicit child node is taken into
2449 account as if it was a normal child cgroup of the root cgroup with a
2450 weight value of 200.
2459 cgroup namespace provides a mechanism to virtualize the view of the
2460 "/proc/$PID/cgroup" file and cgroup mounts. The CLONE_NEWCGROUP clone
2461 flag can be used with clone(2) and unshare(2) to create a new cgroup
2462 namespace. The process running inside the cgroup namespace will have
2463 its "/proc/$PID/cgroup" output restricted to cgroupns root. The
2464 cgroupns root is the cgroup of the process at the time of creation of
2465 the cgroup namespace.
2467 Without cgroup namespace, the "/proc/$PID/cgroup" file shows the
2468 complete path of the cgroup of a process. In a container setup where
2469 a set of cgroups and namespaces are intended to isolate processes the
2470 "/proc/$PID/cgroup" file may leak potential system level information
2471 to the isolated processes. For example::
2473 # cat /proc/self/cgroup
2474 0::/batchjobs/container_id1
2476 The path '/batchjobs/container_id1' can be considered as system-data
2477 and undesirable to expose to the isolated processes. cgroup namespace
2478 can be used to restrict visibility of this path. For example, before
2479 creating a cgroup namespace, one would see::
2481 # ls -l /proc/self/ns/cgroup
2482 lrwxrwxrwx 1 root root 0 2014-07-15 10:37 /proc/self/ns/cgroup -> cgroup:[4026531835]
2483 # cat /proc/self/cgroup
2484 0::/batchjobs/container_id1
2486 After unsharing a new namespace, the view changes::
2488 # ls -l /proc/self/ns/cgroup
2489 lrwxrwxrwx 1 root root 0 2014-07-15 10:35 /proc/self/ns/cgroup -> cgroup:[4026532183]
2490 # cat /proc/self/cgroup
2493 When some thread from a multi-threaded process unshares its cgroup
2494 namespace, the new cgroupns gets applied to the entire process (all
2495 the threads). This is natural for the v2 hierarchy; however, for the
2496 legacy hierarchies, this may be unexpected.
2498 A cgroup namespace is alive as long as there are processes inside or
2499 mounts pinning it. When the last usage goes away, the cgroup
2500 namespace is destroyed. The cgroupns root and the actual cgroups
2507 The 'cgroupns root' for a cgroup namespace is the cgroup in which the
2508 process calling unshare(2) is running. For example, if a process in
2509 /batchjobs/container_id1 cgroup calls unshare, cgroup
2510 /batchjobs/container_id1 becomes the cgroupns root. For the
2511 init_cgroup_ns, this is the real root ('/') cgroup.
2513 The cgroupns root cgroup does not change even if the namespace creator
2514 process later moves to a different cgroup::
2516 # ~/unshare -c # unshare cgroupns in some cgroup
2517 # cat /proc/self/cgroup
2520 # echo 0 > sub_cgrp_1/cgroup.procs
2521 # cat /proc/self/cgroup
2524 Each process gets its namespace-specific view of "/proc/$PID/cgroup"
2526 Processes running inside the cgroup namespace will be able to see
2527 cgroup paths (in /proc/self/cgroup) only inside their root cgroup.
2528 From within an unshared cgroupns::
2532 # echo 7353 > sub_cgrp_1/cgroup.procs
2533 # cat /proc/7353/cgroup
2536 From the initial cgroup namespace, the real cgroup path will be
2539 $ cat /proc/7353/cgroup
2540 0::/batchjobs/container_id1/sub_cgrp_1
2542 From a sibling cgroup namespace (that is, a namespace rooted at a
2543 different cgroup), the cgroup path relative to its own cgroup
2544 namespace root will be shown. For instance, if PID 7353's cgroup
2545 namespace root is at '/batchjobs/container_id2', then it will see::
2547 # cat /proc/7353/cgroup
2548 0::/../container_id2/sub_cgrp_1
2550 Note that the relative path always starts with '/' to indicate that
2551 its relative to the cgroup namespace root of the caller.
2554 Migration and setns(2)
2555 ----------------------
2557 Processes inside a cgroup namespace can move into and out of the
2558 namespace root if they have proper access to external cgroups. For
2559 example, from inside a namespace with cgroupns root at
2560 /batchjobs/container_id1, and assuming that the global hierarchy is
2561 still accessible inside cgroupns::
2563 # cat /proc/7353/cgroup
2565 # echo 7353 > batchjobs/container_id2/cgroup.procs
2566 # cat /proc/7353/cgroup
2567 0::/../container_id2
2569 Note that this kind of setup is not encouraged. A task inside cgroup
2570 namespace should only be exposed to its own cgroupns hierarchy.
2572 setns(2) to another cgroup namespace is allowed when:
2574 (a) the process has CAP_SYS_ADMIN against its current user namespace
2575 (b) the process has CAP_SYS_ADMIN against the target cgroup
2578 No implicit cgroup changes happen with attaching to another cgroup
2579 namespace. It is expected that the someone moves the attaching
2580 process under the target cgroup namespace root.
2583 Interaction with Other Namespaces
2584 ---------------------------------
2586 Namespace specific cgroup hierarchy can be mounted by a process
2587 running inside a non-init cgroup namespace::
2589 # mount -t cgroup2 none $MOUNT_POINT
2591 This will mount the unified cgroup hierarchy with cgroupns root as the
2592 filesystem root. The process needs CAP_SYS_ADMIN against its user and
2595 The virtualization of /proc/self/cgroup file combined with restricting
2596 the view of cgroup hierarchy by namespace-private cgroupfs mount
2597 provides a properly isolated cgroup view inside the container.
2600 Information on Kernel Programming
2601 =================================
2603 This section contains kernel programming information in the areas
2604 where interacting with cgroup is necessary. cgroup core and
2605 controllers are not covered.
2608 Filesystem Support for Writeback
2609 --------------------------------
2611 A filesystem can support cgroup writeback by updating
2612 address_space_operations->writepage[s]() to annotate bio's using the
2613 following two functions.
2615 wbc_init_bio(@wbc, @bio)
2616 Should be called for each bio carrying writeback data and
2617 associates the bio with the inode's owner cgroup and the
2618 corresponding request queue. This must be called after
2619 a queue (device) has been associated with the bio and
2622 wbc_account_cgroup_owner(@wbc, @page, @bytes)
2623 Should be called for each data segment being written out.
2624 While this function doesn't care exactly when it's called
2625 during the writeback session, it's the easiest and most
2626 natural to call it as data segments are added to a bio.
2628 With writeback bio's annotated, cgroup support can be enabled per
2629 super_block by setting SB_I_CGROUPWB in ->s_iflags. This allows for
2630 selective disabling of cgroup writeback support which is helpful when
2631 certain filesystem features, e.g. journaled data mode, are
2634 wbc_init_bio() binds the specified bio to its cgroup. Depending on
2635 the configuration, the bio may be executed at a lower priority and if
2636 the writeback session is holding shared resources, e.g. a journal
2637 entry, may lead to priority inversion. There is no one easy solution
2638 for the problem. Filesystems can try to work around specific problem
2639 cases by skipping wbc_init_bio() and using bio_associate_blkg()
2643 Deprecated v1 Core Features
2644 ===========================
2646 - Multiple hierarchies including named ones are not supported.
2648 - All v1 mount options are not supported.
2650 - The "tasks" file is removed and "cgroup.procs" is not sorted.
2652 - "cgroup.clone_children" is removed.
2654 - /proc/cgroups is meaningless for v2. Use "cgroup.controllers" file
2655 at the root instead.
2658 Issues with v1 and Rationales for v2
2659 ====================================
2661 Multiple Hierarchies
2662 --------------------
2664 cgroup v1 allowed an arbitrary number of hierarchies and each
2665 hierarchy could host any number of controllers. While this seemed to
2666 provide a high level of flexibility, it wasn't useful in practice.
2668 For example, as there is only one instance of each controller, utility
2669 type controllers such as freezer which can be useful in all
2670 hierarchies could only be used in one. The issue is exacerbated by
2671 the fact that controllers couldn't be moved to another hierarchy once
2672 hierarchies were populated. Another issue was that all controllers
2673 bound to a hierarchy were forced to have exactly the same view of the
2674 hierarchy. It wasn't possible to vary the granularity depending on
2675 the specific controller.
2677 In practice, these issues heavily limited which controllers could be
2678 put on the same hierarchy and most configurations resorted to putting
2679 each controller on its own hierarchy. Only closely related ones, such
2680 as the cpu and cpuacct controllers, made sense to be put on the same
2681 hierarchy. This often meant that userland ended up managing multiple
2682 similar hierarchies repeating the same steps on each hierarchy
2683 whenever a hierarchy management operation was necessary.
2685 Furthermore, support for multiple hierarchies came at a steep cost.
2686 It greatly complicated cgroup core implementation but more importantly
2687 the support for multiple hierarchies restricted how cgroup could be
2688 used in general and what controllers was able to do.
2690 There was no limit on how many hierarchies there might be, which meant
2691 that a thread's cgroup membership couldn't be described in finite
2692 length. The key might contain any number of entries and was unlimited
2693 in length, which made it highly awkward to manipulate and led to
2694 addition of controllers which existed only to identify membership,
2695 which in turn exacerbated the original problem of proliferating number
2698 Also, as a controller couldn't have any expectation regarding the
2699 topologies of hierarchies other controllers might be on, each
2700 controller had to assume that all other controllers were attached to
2701 completely orthogonal hierarchies. This made it impossible, or at
2702 least very cumbersome, for controllers to cooperate with each other.
2704 In most use cases, putting controllers on hierarchies which are
2705 completely orthogonal to each other isn't necessary. What usually is
2706 called for is the ability to have differing levels of granularity
2707 depending on the specific controller. In other words, hierarchy may
2708 be collapsed from leaf towards root when viewed from specific
2709 controllers. For example, a given configuration might not care about
2710 how memory is distributed beyond a certain level while still wanting
2711 to control how CPU cycles are distributed.
2717 cgroup v1 allowed threads of a process to belong to different cgroups.
2718 This didn't make sense for some controllers and those controllers
2719 ended up implementing different ways to ignore such situations but
2720 much more importantly it blurred the line between API exposed to
2721 individual applications and system management interface.
2723 Generally, in-process knowledge is available only to the process
2724 itself; thus, unlike service-level organization of processes,
2725 categorizing threads of a process requires active participation from
2726 the application which owns the target process.
2728 cgroup v1 had an ambiguously defined delegation model which got abused
2729 in combination with thread granularity. cgroups were delegated to
2730 individual applications so that they can create and manage their own
2731 sub-hierarchies and control resource distributions along them. This
2732 effectively raised cgroup to the status of a syscall-like API exposed
2735 First of all, cgroup has a fundamentally inadequate interface to be
2736 exposed this way. For a process to access its own knobs, it has to
2737 extract the path on the target hierarchy from /proc/self/cgroup,
2738 construct the path by appending the name of the knob to the path, open
2739 and then read and/or write to it. This is not only extremely clunky
2740 and unusual but also inherently racy. There is no conventional way to
2741 define transaction across the required steps and nothing can guarantee
2742 that the process would actually be operating on its own sub-hierarchy.
2744 cgroup controllers implemented a number of knobs which would never be
2745 accepted as public APIs because they were just adding control knobs to
2746 system-management pseudo filesystem. cgroup ended up with interface
2747 knobs which were not properly abstracted or refined and directly
2748 revealed kernel internal details. These knobs got exposed to
2749 individual applications through the ill-defined delegation mechanism
2750 effectively abusing cgroup as a shortcut to implementing public APIs
2751 without going through the required scrutiny.
2753 This was painful for both userland and kernel. Userland ended up with
2754 misbehaving and poorly abstracted interfaces and kernel exposing and
2755 locked into constructs inadvertently.
2758 Competition Between Inner Nodes and Threads
2759 -------------------------------------------
2761 cgroup v1 allowed threads to be in any cgroups which created an
2762 interesting problem where threads belonging to a parent cgroup and its
2763 children cgroups competed for resources. This was nasty as two
2764 different types of entities competed and there was no obvious way to
2765 settle it. Different controllers did different things.
2767 The cpu controller considered threads and cgroups as equivalents and
2768 mapped nice levels to cgroup weights. This worked for some cases but
2769 fell flat when children wanted to be allocated specific ratios of CPU
2770 cycles and the number of internal threads fluctuated - the ratios
2771 constantly changed as the number of competing entities fluctuated.
2772 There also were other issues. The mapping from nice level to weight
2773 wasn't obvious or universal, and there were various other knobs which
2774 simply weren't available for threads.
2776 The io controller implicitly created a hidden leaf node for each
2777 cgroup to host the threads. The hidden leaf had its own copies of all
2778 the knobs with ``leaf_`` prefixed. While this allowed equivalent
2779 control over internal threads, it was with serious drawbacks. It
2780 always added an extra layer of nesting which wouldn't be necessary
2781 otherwise, made the interface messy and significantly complicated the
2784 The memory controller didn't have a way to control what happened
2785 between internal tasks and child cgroups and the behavior was not
2786 clearly defined. There were attempts to add ad-hoc behaviors and
2787 knobs to tailor the behavior to specific workloads which would have
2788 led to problems extremely difficult to resolve in the long term.
2790 Multiple controllers struggled with internal tasks and came up with
2791 different ways to deal with it; unfortunately, all the approaches were
2792 severely flawed and, furthermore, the widely different behaviors
2793 made cgroup as a whole highly inconsistent.
2795 This clearly is a problem which needs to be addressed from cgroup core
2799 Other Interface Issues
2800 ----------------------
2802 cgroup v1 grew without oversight and developed a large number of
2803 idiosyncrasies and inconsistencies. One issue on the cgroup core side
2804 was how an empty cgroup was notified - a userland helper binary was
2805 forked and executed for each event. The event delivery wasn't
2806 recursive or delegatable. The limitations of the mechanism also led
2807 to in-kernel event delivery filtering mechanism further complicating
2810 Controller interfaces were problematic too. An extreme example is
2811 controllers completely ignoring hierarchical organization and treating
2812 all cgroups as if they were all located directly under the root
2813 cgroup. Some controllers exposed a large amount of inconsistent
2814 implementation details to userland.
2816 There also was no consistency across controllers. When a new cgroup
2817 was created, some controllers defaulted to not imposing extra
2818 restrictions while others disallowed any resource usage until
2819 explicitly configured. Configuration knobs for the same type of
2820 control used widely differing naming schemes and formats. Statistics
2821 and information knobs were named arbitrarily and used different
2822 formats and units even in the same controller.
2824 cgroup v2 establishes common conventions where appropriate and updates
2825 controllers so that they expose minimal and consistent interfaces.
2828 Controller Issues and Remedies
2829 ------------------------------
2834 The original lower boundary, the soft limit, is defined as a limit
2835 that is per default unset. As a result, the set of cgroups that
2836 global reclaim prefers is opt-in, rather than opt-out. The costs for
2837 optimizing these mostly negative lookups are so high that the
2838 implementation, despite its enormous size, does not even provide the
2839 basic desirable behavior. First off, the soft limit has no
2840 hierarchical meaning. All configured groups are organized in a global
2841 rbtree and treated like equal peers, regardless where they are located
2842 in the hierarchy. This makes subtree delegation impossible. Second,
2843 the soft limit reclaim pass is so aggressive that it not just
2844 introduces high allocation latencies into the system, but also impacts
2845 system performance due to overreclaim, to the point where the feature
2846 becomes self-defeating.
2848 The memory.low boundary on the other hand is a top-down allocated
2849 reserve. A cgroup enjoys reclaim protection when it's within its
2850 effective low, which makes delegation of subtrees possible. It also
2851 enjoys having reclaim pressure proportional to its overage when
2852 above its effective low.
2854 The original high boundary, the hard limit, is defined as a strict
2855 limit that can not budge, even if the OOM killer has to be called.
2856 But this generally goes against the goal of making the most out of the
2857 available memory. The memory consumption of workloads varies during
2858 runtime, and that requires users to overcommit. But doing that with a
2859 strict upper limit requires either a fairly accurate prediction of the
2860 working set size or adding slack to the limit. Since working set size
2861 estimation is hard and error prone, and getting it wrong results in
2862 OOM kills, most users tend to err on the side of a looser limit and
2863 end up wasting precious resources.
2865 The memory.high boundary on the other hand can be set much more
2866 conservatively. When hit, it throttles allocations by forcing them
2867 into direct reclaim to work off the excess, but it never invokes the
2868 OOM killer. As a result, a high boundary that is chosen too
2869 aggressively will not terminate the processes, but instead it will
2870 lead to gradual performance degradation. The user can monitor this
2871 and make corrections until the minimal memory footprint that still
2872 gives acceptable performance is found.
2874 In extreme cases, with many concurrent allocations and a complete
2875 breakdown of reclaim progress within the group, the high boundary can
2876 be exceeded. But even then it's mostly better to satisfy the
2877 allocation from the slack available in other groups or the rest of the
2878 system than killing the group. Otherwise, memory.max is there to
2879 limit this type of spillover and ultimately contain buggy or even
2880 malicious applications.
2882 Setting the original memory.limit_in_bytes below the current usage was
2883 subject to a race condition, where concurrent charges could cause the
2884 limit setting to fail. memory.max on the other hand will first set the
2885 limit to prevent new charges, and then reclaim and OOM kill until the
2886 new limit is met - or the task writing to memory.max is killed.
2888 The combined memory+swap accounting and limiting is replaced by real
2889 control over swap space.
2891 The main argument for a combined memory+swap facility in the original
2892 cgroup design was that global or parental pressure would always be
2893 able to swap all anonymous memory of a child group, regardless of the
2894 child's own (possibly untrusted) configuration. However, untrusted
2895 groups can sabotage swapping by other means - such as referencing its
2896 anonymous memory in a tight loop - and an admin can not assume full
2897 swappability when overcommitting untrusted jobs.
2899 For trusted jobs, on the other hand, a combined counter is not an
2900 intuitive userspace interface, and it flies in the face of the idea
2901 that cgroup controllers should account and limit specific physical
2902 resources. Swap space is a resource like all others in the system,
2903 and that's why unified hierarchy allows distributing it separately.