About Kernel Documentation Linux Kernel Contact Linux Resources Linux Blog

Documentation / cgroup-v2.txt

Custom Search

Based on kernel version 4.16.1. Page generated on 2018-04-09 11:52 EST.

1	================
2	Control Group v2
3	================
5	:Date: October, 2015
6	:Author: Tejun Heo <tj@kernel.org>
8	This is the authoritative documentation on the design, interface and
9	conventions of cgroup v2.  It describes all userland-visible aspects
10	of cgroup including core and specific controller behaviors.  All
11	future changes must be reflected in this document.  Documentation for
12	v1 is available under Documentation/cgroup-v1/.
16	   1. Introduction
17	     1-1. Terminology
18	     1-2. What is cgroup?
19	   2. Basic Operations
20	     2-1. Mounting
21	     2-2. Organizing Processes and Threads
22	       2-2-1. Processes
23	       2-2-2. Threads
24	     2-3. [Un]populated Notification
25	     2-4. Controlling Controllers
26	       2-4-1. Enabling and Disabling
27	       2-4-2. Top-down Constraint
28	       2-4-3. No Internal Process Constraint
29	     2-5. Delegation
30	       2-5-1. Model of Delegation
31	       2-5-2. Delegation Containment
32	     2-6. Guidelines
33	       2-6-1. Organize Once and Control
34	       2-6-2. Avoid Name Collisions
35	   3. Resource Distribution Models
36	     3-1. Weights
37	     3-2. Limits
38	     3-3. Protections
39	     3-4. Allocations
40	   4. Interface Files
41	     4-1. Format
42	     4-2. Conventions
43	     4-3. Core Interface Files
44	   5. Controllers
45	     5-1. CPU
46	       5-1-1. CPU Interface Files
47	     5-2. Memory
48	       5-2-1. Memory Interface Files
49	       5-2-2. Usage Guidelines
50	       5-2-3. Memory Ownership
51	     5-3. IO
52	       5-3-1. IO Interface Files
53	       5-3-2. Writeback
54	     5-4. PID
55	       5-4-1. PID Interface Files
56	     5-5. Device
57	     5-6. RDMA
58	       5-6-1. RDMA Interface Files
59	     5-7. Misc
60	       5-7-1. perf_event
61	     5-N. Non-normative information
62	       5-N-1. CPU controller root cgroup process behaviour
63	       5-N-2. IO controller root cgroup process behaviour
64	   6. Namespace
65	     6-1. Basics
66	     6-2. The Root and Views
67	     6-3. Migration and setns(2)
68	     6-4. Interaction with Other Namespaces
69	   P. Information on Kernel Programming
70	     P-1. Filesystem Support for Writeback
71	   D. Deprecated v1 Core Features
72	   R. Issues with v1 and Rationales for v2
73	     R-1. Multiple Hierarchies
74	     R-2. Thread Granularity
75	     R-3. Competition Between Inner Nodes and Threads
76	     R-4. Other Interface Issues
77	     R-5. Controller Issues and Remedies
78	       R-5-1. Memory
81	Introduction
82	============
84	Terminology
85	-----------
87	"cgroup" stands for "control group" and is never capitalized.  The
88	singular form is used to designate the whole feature and also as a
89	qualifier as in "cgroup controllers".  When explicitly referring to
90	multiple individual control groups, the plural form "cgroups" is used.
93	What is cgroup?
94	---------------
96	cgroup is a mechanism to organize processes hierarchically and
97	distribute system resources along the hierarchy in a controlled and
98	configurable manner.
100	cgroup is largely composed of two parts - the core and controllers.
101	cgroup core is primarily responsible for hierarchically organizing
102	processes.  A cgroup controller is usually responsible for
103	distributing a specific type of system resource along the hierarchy
104	although there are utility controllers which serve purposes other than
105	resource distribution.
107	cgroups form a tree structure and every process in the system belongs
108	to one and only one cgroup.  All threads of a process belong to the
109	same cgroup.  On creation, all processes are put in the cgroup that
110	the parent process belongs to at the time.  A process can be migrated
111	to another cgroup.  Migration of a process doesn't affect already
112	existing descendant processes.
114	Following certain structural constraints, controllers may be enabled or
115	disabled selectively on a cgroup.  All controller behaviors are
116	hierarchical - if a controller is enabled on a cgroup, it affects all
117	processes which belong to the cgroups consisting the inclusive
118	sub-hierarchy of the cgroup.  When a controller is enabled on a nested
119	cgroup, it always restricts the resource distribution further.  The
120	restrictions set closer to the root in the hierarchy can not be
121	overridden from further away.
124	Basic Operations
125	================
127	Mounting
128	--------
130	Unlike v1, cgroup v2 has only single hierarchy.  The cgroup v2
131	hierarchy can be mounted with the following mount command::
133	  # mount -t cgroup2 none $MOUNT_POINT
135	cgroup2 filesystem has the magic number 0x63677270 ("cgrp").  All
136	controllers which support v2 and are not bound to a v1 hierarchy are
137	automatically bound to the v2 hierarchy and show up at the root.
138	Controllers which are not in active use in the v2 hierarchy can be
139	bound to other hierarchies.  This allows mixing v2 hierarchy with the
140	legacy v1 multiple hierarchies in a fully backward compatible way.
142	A controller can be moved across hierarchies only after the controller
143	is no longer referenced in its current hierarchy.  Because per-cgroup
144	controller states are destroyed asynchronously and controllers may
145	have lingering references, a controller may not show up immediately on
146	the v2 hierarchy after the final umount of the previous hierarchy.
147	Similarly, a controller should be fully disabled to be moved out of
148	the unified hierarchy and it may take some time for the disabled
149	controller to become available for other hierarchies; furthermore, due
150	to inter-controller dependencies, other controllers may need to be
151	disabled too.
153	While useful for development and manual configurations, moving
154	controllers dynamically between the v2 and other hierarchies is
155	strongly discouraged for production use.  It is recommended to decide
156	the hierarchies and controller associations before starting using the
157	controllers after system boot.
159	During transition to v2, system management software might still
160	automount the v1 cgroup filesystem and so hijack all controllers
161	during boot, before manual intervention is possible. To make testing
162	and experimenting easier, the kernel parameter cgroup_no_v1= allows
163	disabling controllers in v1 and make them always available in v2.
165	cgroup v2 currently supports the following mount options.
167	  nsdelegate
169		Consider cgroup namespaces as delegation boundaries.  This
170		option is system wide and can only be set on mount or modified
171		through remount from the init namespace.  The mount option is
172		ignored on non-init namespace mounts.  Please refer to the
173		Delegation section for details.
176	Organizing Processes and Threads
177	--------------------------------
179	Processes
180	~~~~~~~~~
182	Initially, only the root cgroup exists to which all processes belong.
183	A child cgroup can be created by creating a sub-directory::
185	  # mkdir $CGROUP_NAME
187	A given cgroup may have multiple child cgroups forming a tree
188	structure.  Each cgroup has a read-writable interface file
189	"cgroup.procs".  When read, it lists the PIDs of all processes which
190	belong to the cgroup one-per-line.  The PIDs are not ordered and the
191	same PID may show up more than once if the process got moved to
192	another cgroup and then back or the PID got recycled while reading.
194	A process can be migrated into a cgroup by writing its PID to the
195	target cgroup's "cgroup.procs" file.  Only one process can be migrated
196	on a single write(2) call.  If a process is composed of multiple
197	threads, writing the PID of any thread migrates all threads of the
198	process.
200	When a process forks a child process, the new process is born into the
201	cgroup that the forking process belongs to at the time of the
202	operation.  After exit, a process stays associated with the cgroup
203	that it belonged to at the time of exit until it's reaped; however, a
204	zombie process does not appear in "cgroup.procs" and thus can't be
205	moved to another cgroup.
207	A cgroup which doesn't have any children or live processes can be
208	destroyed by removing the directory.  Note that a cgroup which doesn't
209	have any children and is associated only with zombie processes is
210	considered empty and can be removed::
212	  # rmdir $CGROUP_NAME
214	"/proc/$PID/cgroup" lists a process's cgroup membership.  If legacy
215	cgroup is in use in the system, this file may contain multiple lines,
216	one for each hierarchy.  The entry for cgroup v2 is always in the
217	format "0::$PATH"::
219	  # cat /proc/842/cgroup
220	  ...
221	  0::/test-cgroup/test-cgroup-nested
223	If the process becomes a zombie and the cgroup it was associated with
224	is removed subsequently, " (deleted)" is appended to the path::
226	  # cat /proc/842/cgroup
227	  ...
228	  0::/test-cgroup/test-cgroup-nested (deleted)
231	Threads
232	~~~~~~~
234	cgroup v2 supports thread granularity for a subset of controllers to
235	support use cases requiring hierarchical resource distribution across
236	the threads of a group of processes.  By default, all threads of a
237	process belong to the same cgroup, which also serves as the resource
238	domain to host resource consumptions which are not specific to a
239	process or thread.  The thread mode allows threads to be spread across
240	a subtree while still maintaining the common resource domain for them.
242	Controllers which support thread mode are called threaded controllers.
243	The ones which don't are called domain controllers.
245	Marking a cgroup threaded makes it join the resource domain of its
246	parent as a threaded cgroup.  The parent may be another threaded
247	cgroup whose resource domain is further up in the hierarchy.  The root
248	of a threaded subtree, that is, the nearest ancestor which is not
249	threaded, is called threaded domain or thread root interchangeably and
250	serves as the resource domain for the entire subtree.
252	Inside a threaded subtree, threads of a process can be put in
253	different cgroups and are not subject to the no internal process
254	constraint - threaded controllers can be enabled on non-leaf cgroups
255	whether they have threads in them or not.
257	As the threaded domain cgroup hosts all the domain resource
258	consumptions of the subtree, it is considered to have internal
259	resource consumptions whether there are processes in it or not and
260	can't have populated child cgroups which aren't threaded.  Because the
261	root cgroup is not subject to no internal process constraint, it can
262	serve both as a threaded domain and a parent to domain cgroups.
264	The current operation mode or type of the cgroup is shown in the
265	"cgroup.type" file which indicates whether the cgroup is a normal
266	domain, a domain which is serving as the domain of a threaded subtree,
267	or a threaded cgroup.
269	On creation, a cgroup is always a domain cgroup and can be made
270	threaded by writing "threaded" to the "cgroup.type" file.  The
271	operation is single direction::
273	  # echo threaded > cgroup.type
275	Once threaded, the cgroup can't be made a domain again.  To enable the
276	thread mode, the following conditions must be met.
278	- As the cgroup will join the parent's resource domain.  The parent
279	  must either be a valid (threaded) domain or a threaded cgroup.
281	- When the parent is an unthreaded domain, it must not have any domain
282	  controllers enabled or populated domain children.  The root is
283	  exempt from this requirement.
285	Topology-wise, a cgroup can be in an invalid state.  Please consider
286	the following topology::
288	  A (threaded domain) - B (threaded) - C (domain, just created)
290	C is created as a domain but isn't connected to a parent which can
291	host child domains.  C can't be used until it is turned into a
292	threaded cgroup.  "cgroup.type" file will report "domain (invalid)" in
293	these cases.  Operations which fail due to invalid topology use
294	EOPNOTSUPP as the errno.
296	A domain cgroup is turned into a threaded domain when one of its child
297	cgroup becomes threaded or threaded controllers are enabled in the
298	"cgroup.subtree_control" file while there are processes in the cgroup.
299	A threaded domain reverts to a normal domain when the conditions
300	clear.
302	When read, "cgroup.threads" contains the list of the thread IDs of all
303	threads in the cgroup.  Except that the operations are per-thread
304	instead of per-process, "cgroup.threads" has the same format and
305	behaves the same way as "cgroup.procs".  While "cgroup.threads" can be
306	written to in any cgroup, as it can only move threads inside the same
307	threaded domain, its operations are confined inside each threaded
308	subtree.
310	The threaded domain cgroup serves as the resource domain for the whole
311	subtree, and, while the threads can be scattered across the subtree,
312	all the processes are considered to be in the threaded domain cgroup.
313	"cgroup.procs" in a threaded domain cgroup contains the PIDs of all
314	processes in the subtree and is not readable in the subtree proper.
315	However, "cgroup.procs" can be written to from anywhere in the subtree
316	to migrate all threads of the matching process to the cgroup.
318	Only threaded controllers can be enabled in a threaded subtree.  When
319	a threaded controller is enabled inside a threaded subtree, it only
320	accounts for and controls resource consumptions associated with the
321	threads in the cgroup and its descendants.  All consumptions which
322	aren't tied to a specific thread belong to the threaded domain cgroup.
324	Because a threaded subtree is exempt from no internal process
325	constraint, a threaded controller must be able to handle competition
326	between threads in a non-leaf cgroup and its child cgroups.  Each
327	threaded controller defines how such competitions are handled.
330	[Un]populated Notification
331	--------------------------
333	Each non-root cgroup has a "cgroup.events" file which contains
334	"populated" field indicating whether the cgroup's sub-hierarchy has
335	live processes in it.  Its value is 0 if there is no live process in
336	the cgroup and its descendants; otherwise, 1.  poll and [id]notify
337	events are triggered when the value changes.  This can be used, for
338	example, to start a clean-up operation after all processes of a given
339	sub-hierarchy have exited.  The populated state updates and
340	notifications are recursive.  Consider the following sub-hierarchy
341	where the numbers in the parentheses represent the numbers of processes
342	in each cgroup::
344	  A(4) - B(0) - C(1)
345	              \ D(0)
347	A, B and C's "populated" fields would be 1 while D's 0.  After the one
348	process in C exits, B and C's "populated" fields would flip to "0" and
349	file modified events will be generated on the "cgroup.events" files of
350	both cgroups.
353	Controlling Controllers
354	-----------------------
356	Enabling and Disabling
357	~~~~~~~~~~~~~~~~~~~~~~
359	Each cgroup has a "cgroup.controllers" file which lists all
360	controllers available for the cgroup to enable::
362	  # cat cgroup.controllers
363	  cpu io memory
365	No controller is enabled by default.  Controllers can be enabled and
366	disabled by writing to the "cgroup.subtree_control" file::
368	  # echo "+cpu +memory -io" > cgroup.subtree_control
370	Only controllers which are listed in "cgroup.controllers" can be
371	enabled.  When multiple operations are specified as above, either they
372	all succeed or fail.  If multiple operations on the same controller
373	are specified, the last one is effective.
375	Enabling a controller in a cgroup indicates that the distribution of
376	the target resource across its immediate children will be controlled.
377	Consider the following sub-hierarchy.  The enabled controllers are
378	listed in parentheses::
380	  A(cpu,memory) - B(memory) - C()
381	                            \ D()
383	As A has "cpu" and "memory" enabled, A will control the distribution
384	of CPU cycles and memory to its children, in this case, B.  As B has
385	"memory" enabled but not "CPU", C and D will compete freely on CPU
386	cycles but their division of memory available to B will be controlled.
388	As a controller regulates the distribution of the target resource to
389	the cgroup's children, enabling it creates the controller's interface
390	files in the child cgroups.  In the above example, enabling "cpu" on B
391	would create the "cpu." prefixed controller interface files in C and
392	D.  Likewise, disabling "memory" from B would remove the "memory."
393	prefixed controller interface files from C and D.  This means that the
394	controller interface files - anything which doesn't start with
395	"cgroup." are owned by the parent rather than the cgroup itself.
398	Top-down Constraint
399	~~~~~~~~~~~~~~~~~~~
401	Resources are distributed top-down and a cgroup can further distribute
402	a resource only if the resource has been distributed to it from the
403	parent.  This means that all non-root "cgroup.subtree_control" files
404	can only contain controllers which are enabled in the parent's
405	"cgroup.subtree_control" file.  A controller can be enabled only if
406	the parent has the controller enabled and a controller can't be
407	disabled if one or more children have it enabled.
410	No Internal Process Constraint
411	~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
413	Non-root cgroups can distribute domain resources to their children
414	only when they don't have any processes of their own.  In other words,
415	only domain cgroups which don't contain any processes can have domain
416	controllers enabled in their "cgroup.subtree_control" files.
418	This guarantees that, when a domain controller is looking at the part
419	of the hierarchy which has it enabled, processes are always only on
420	the leaves.  This rules out situations where child cgroups compete
421	against internal processes of the parent.
423	The root cgroup is exempt from this restriction.  Root contains
424	processes and anonymous resource consumption which can't be associated
425	with any other cgroups and requires special treatment from most
426	controllers.  How resource consumption in the root cgroup is governed
427	is up to each controller (for more information on this topic please
428	refer to the Non-normative information section in the Controllers
429	chapter).
431	Note that the restriction doesn't get in the way if there is no
432	enabled controller in the cgroup's "cgroup.subtree_control".  This is
433	important as otherwise it wouldn't be possible to create children of a
434	populated cgroup.  To control resource distribution of a cgroup, the
435	cgroup must create children and transfer all its processes to the
436	children before enabling controllers in its "cgroup.subtree_control"
437	file.
440	Delegation
441	----------
443	Model of Delegation
444	~~~~~~~~~~~~~~~~~~~
446	A cgroup can be delegated in two ways.  First, to a less privileged
447	user by granting write access of the directory and its "cgroup.procs",
448	"cgroup.threads" and "cgroup.subtree_control" files to the user.
449	Second, if the "nsdelegate" mount option is set, automatically to a
450	cgroup namespace on namespace creation.
452	Because the resource control interface files in a given directory
453	control the distribution of the parent's resources, the delegatee
454	shouldn't be allowed to write to them.  For the first method, this is
455	achieved by not granting access to these files.  For the second, the
456	kernel rejects writes to all files other than "cgroup.procs" and
457	"cgroup.subtree_control" on a namespace root from inside the
458	namespace.
460	The end results are equivalent for both delegation types.  Once
461	delegated, the user can build sub-hierarchy under the directory,
462	organize processes inside it as it sees fit and further distribute the
463	resources it received from the parent.  The limits and other settings
464	of all resource controllers are hierarchical and regardless of what
465	happens in the delegated sub-hierarchy, nothing can escape the
466	resource restrictions imposed by the parent.
468	Currently, cgroup doesn't impose any restrictions on the number of
469	cgroups in or nesting depth of a delegated sub-hierarchy; however,
470	this may be limited explicitly in the future.
473	Delegation Containment
474	~~~~~~~~~~~~~~~~~~~~~~
476	A delegated sub-hierarchy is contained in the sense that processes
477	can't be moved into or out of the sub-hierarchy by the delegatee.
479	For delegations to a less privileged user, this is achieved by
480	requiring the following conditions for a process with a non-root euid
481	to migrate a target process into a cgroup by writing its PID to the
482	"cgroup.procs" file.
484	- The writer must have write access to the "cgroup.procs" file.
486	- The writer must have write access to the "cgroup.procs" file of the
487	  common ancestor of the source and destination cgroups.
489	The above two constraints ensure that while a delegatee may migrate
490	processes around freely in the delegated sub-hierarchy it can't pull
491	in from or push out to outside the sub-hierarchy.
493	For an example, let's assume cgroups C0 and C1 have been delegated to
494	user U0 who created C00, C01 under C0 and C10 under C1 as follows and
495	all processes under C0 and C1 belong to U0::
497	  ~~~~~~~~~~~~~ - C0 - C00
498	  ~ cgroup    ~      \ C01
499	  ~ hierarchy ~
500	  ~~~~~~~~~~~~~ - C1 - C10
502	Let's also say U0 wants to write the PID of a process which is
503	currently in C10 into "C00/cgroup.procs".  U0 has write access to the
504	file; however, the common ancestor of the source cgroup C10 and the
505	destination cgroup C00 is above the points of delegation and U0 would
506	not have write access to its "cgroup.procs" files and thus the write
507	will be denied with -EACCES.
509	For delegations to namespaces, containment is achieved by requiring
510	that both the source and destination cgroups are reachable from the
511	namespace of the process which is attempting the migration.  If either
512	is not reachable, the migration is rejected with -ENOENT.
515	Guidelines
516	----------
518	Organize Once and Control
519	~~~~~~~~~~~~~~~~~~~~~~~~~
521	Migrating a process across cgroups is a relatively expensive operation
522	and stateful resources such as memory are not moved together with the
523	process.  This is an explicit design decision as there often exist
524	inherent trade-offs between migration and various hot paths in terms
525	of synchronization cost.
527	As such, migrating processes across cgroups frequently as a means to
528	apply different resource restrictions is discouraged.  A workload
529	should be assigned to a cgroup according to the system's logical and
530	resource structure once on start-up.  Dynamic adjustments to resource
531	distribution can be made by changing controller configuration through
532	the interface files.
535	Avoid Name Collisions
536	~~~~~~~~~~~~~~~~~~~~~
538	Interface files for a cgroup and its children cgroups occupy the same
539	directory and it is possible to create children cgroups which collide
540	with interface files.
542	All cgroup core interface files are prefixed with "cgroup." and each
543	controller's interface files are prefixed with the controller name and
544	a dot.  A controller's name is composed of lower case alphabets and
545	'_'s but never begins with an '_' so it can be used as the prefix
546	character for collision avoidance.  Also, interface file names won't
547	start or end with terms which are often used in categorizing workloads
548	such as job, service, slice, unit or workload.
550	cgroup doesn't do anything to prevent name collisions and it's the
551	user's responsibility to avoid them.
554	Resource Distribution Models
555	============================
557	cgroup controllers implement several resource distribution schemes
558	depending on the resource type and expected use cases.  This section
559	describes major schemes in use along with their expected behaviors.
562	Weights
563	-------
565	A parent's resource is distributed by adding up the weights of all
566	active children and giving each the fraction matching the ratio of its
567	weight against the sum.  As only children which can make use of the
568	resource at the moment participate in the distribution, this is
569	work-conserving.  Due to the dynamic nature, this model is usually
570	used for stateless resources.
572	All weights are in the range [1, 10000] with the default at 100.  This
573	allows symmetric multiplicative biases in both directions at fine
574	enough granularity while staying in the intuitive range.
576	As long as the weight is in range, all configuration combinations are
577	valid and there is no reason to reject configuration changes or
578	process migrations.
580	"cpu.weight" proportionally distributes CPU cycles to active children
581	and is an example of this type.
584	Limits
585	------
587	A child can only consume upto the configured amount of the resource.
588	Limits can be over-committed - the sum of the limits of children can
589	exceed the amount of resource available to the parent.
591	Limits are in the range [0, max] and defaults to "max", which is noop.
593	As limits can be over-committed, all configuration combinations are
594	valid and there is no reason to reject configuration changes or
595	process migrations.
597	"io.max" limits the maximum BPS and/or IOPS that a cgroup can consume
598	on an IO device and is an example of this type.
601	Protections
602	-----------
604	A cgroup is protected to be allocated upto the configured amount of
605	the resource if the usages of all its ancestors are under their
606	protected levels.  Protections can be hard guarantees or best effort
607	soft boundaries.  Protections can also be over-committed in which case
608	only upto the amount available to the parent is protected among
609	children.
611	Protections are in the range [0, max] and defaults to 0, which is
612	noop.
614	As protections can be over-committed, all configuration combinations
615	are valid and there is no reason to reject configuration changes or
616	process migrations.
618	"memory.low" implements best-effort memory protection and is an
619	example of this type.
622	Allocations
623	-----------
625	A cgroup is exclusively allocated a certain amount of a finite
626	resource.  Allocations can't be over-committed - the sum of the
627	allocations of children can not exceed the amount of resource
628	available to the parent.
630	Allocations are in the range [0, max] and defaults to 0, which is no
631	resource.
633	As allocations can't be over-committed, some configuration
634	combinations are invalid and should be rejected.  Also, if the
635	resource is mandatory for execution of processes, process migrations
636	may be rejected.
638	"cpu.rt.max" hard-allocates realtime slices and is an example of this
639	type.
642	Interface Files
643	===============
645	Format
646	------
648	All interface files should be in one of the following formats whenever
649	possible::
651	  New-line separated values
652	  (when only one value can be written at once)
654		VAL0\n
655		VAL1\n
656		...
658	  Space separated values
659	  (when read-only or multiple values can be written at once)
661		VAL0 VAL1 ...\n
663	  Flat keyed
665		KEY0 VAL0\n
666		KEY1 VAL1\n
667		...
669	  Nested keyed
671		KEY0 SUB_KEY0=VAL00 SUB_KEY1=VAL01...
672		KEY1 SUB_KEY0=VAL10 SUB_KEY1=VAL11...
673		...
675	For a writable file, the format for writing should generally match
676	reading; however, controllers may allow omitting later fields or
677	implement restricted shortcuts for most common use cases.
679	For both flat and nested keyed files, only the values for a single key
680	can be written at a time.  For nested keyed files, the sub key pairs
681	may be specified in any order and not all pairs have to be specified.
684	Conventions
685	-----------
687	- Settings for a single feature should be contained in a single file.
689	- The root cgroup should be exempt from resource control and thus
690	  shouldn't have resource control interface files.  Also,
691	  informational files on the root cgroup which end up showing global
692	  information available elsewhere shouldn't exist.
694	- If a controller implements weight based resource distribution, its
695	  interface file should be named "weight" and have the range [1,
696	  10000] with 100 as the default.  The values are chosen to allow
697	  enough and symmetric bias in both directions while keeping it
698	  intuitive (the default is 100%).
700	- If a controller implements an absolute resource guarantee and/or
701	  limit, the interface files should be named "min" and "max"
702	  respectively.  If a controller implements best effort resource
703	  guarantee and/or limit, the interface files should be named "low"
704	  and "high" respectively.
706	  In the above four control files, the special token "max" should be
707	  used to represent upward infinity for both reading and writing.
709	- If a setting has a configurable default value and keyed specific
710	  overrides, the default entry should be keyed with "default" and
711	  appear as the first entry in the file.
713	  The default value can be updated by writing either "default $VAL" or
714	  "$VAL".
716	  When writing to update a specific override, "default" can be used as
717	  the value to indicate removal of the override.  Override entries
718	  with "default" as the value must not appear when read.
720	  For example, a setting which is keyed by major:minor device numbers
721	  with integer values may look like the following::
723	    # cat cgroup-example-interface-file
724	    default 150
725	    8:0 300
727	  The default value can be updated by::
729	    # echo 125 > cgroup-example-interface-file
731	  or::
733	    # echo "default 125" > cgroup-example-interface-file
735	  An override can be set by::
737	    # echo "8:16 170" > cgroup-example-interface-file
739	  and cleared by::
741	    # echo "8:0 default" > cgroup-example-interface-file
742	    # cat cgroup-example-interface-file
743	    default 125
744	    8:16 170
746	- For events which are not very high frequency, an interface file
747	  "events" should be created which lists event key value pairs.
748	  Whenever a notifiable event happens, file modified event should be
749	  generated on the file.
752	Core Interface Files
753	--------------------
755	All cgroup core files are prefixed with "cgroup."
757	  cgroup.type
759		A read-write single value file which exists on non-root
760		cgroups.
762		When read, it indicates the current type of the cgroup, which
763		can be one of the following values.
765		- "domain" : A normal valid domain cgroup.
767		- "domain threaded" : A threaded domain cgroup which is
768	          serving as the root of a threaded subtree.
770		- "domain invalid" : A cgroup which is in an invalid state.
771		  It can't be populated or have controllers enabled.  It may
772		  be allowed to become a threaded cgroup.
774		- "threaded" : A threaded cgroup which is a member of a
775	          threaded subtree.
777		A cgroup can be turned into a threaded cgroup by writing
778		"threaded" to this file.
780	  cgroup.procs
781		A read-write new-line separated values file which exists on
782		all cgroups.
784		When read, it lists the PIDs of all processes which belong to
785		the cgroup one-per-line.  The PIDs are not ordered and the
786		same PID may show up more than once if the process got moved
787		to another cgroup and then back or the PID got recycled while
788		reading.
790		A PID can be written to migrate the process associated with
791		the PID to the cgroup.  The writer should match all of the
792		following conditions.
794		- It must have write access to the "cgroup.procs" file.
796		- It must have write access to the "cgroup.procs" file of the
797		  common ancestor of the source and destination cgroups.
799		When delegating a sub-hierarchy, write access to this file
800		should be granted along with the containing directory.
802		In a threaded cgroup, reading this file fails with EOPNOTSUPP
803		as all the processes belong to the thread root.  Writing is
804		supported and moves every thread of the process to the cgroup.
806	  cgroup.threads
807		A read-write new-line separated values file which exists on
808		all cgroups.
810		When read, it lists the TIDs of all threads which belong to
811		the cgroup one-per-line.  The TIDs are not ordered and the
812		same TID may show up more than once if the thread got moved to
813		another cgroup and then back or the TID got recycled while
814		reading.
816		A TID can be written to migrate the thread associated with the
817		TID to the cgroup.  The writer should match all of the
818		following conditions.
820		- It must have write access to the "cgroup.threads" file.
822		- The cgroup that the thread is currently in must be in the
823	          same resource domain as the destination cgroup.
825		- It must have write access to the "cgroup.procs" file of the
826		  common ancestor of the source and destination cgroups.
828		When delegating a sub-hierarchy, write access to this file
829		should be granted along with the containing directory.
831	  cgroup.controllers
832		A read-only space separated values file which exists on all
833		cgroups.
835		It shows space separated list of all controllers available to
836		the cgroup.  The controllers are not ordered.
838	  cgroup.subtree_control
839		A read-write space separated values file which exists on all
840		cgroups.  Starts out empty.
842		When read, it shows space separated list of the controllers
843		which are enabled to control resource distribution from the
844		cgroup to its children.
846		Space separated list of controllers prefixed with '+' or '-'
847		can be written to enable or disable controllers.  A controller
848		name prefixed with '+' enables the controller and '-'
849		disables.  If a controller appears more than once on the list,
850		the last one is effective.  When multiple enable and disable
851		operations are specified, either all succeed or all fail.
853	  cgroup.events
854		A read-only flat-keyed file which exists on non-root cgroups.
855		The following entries are defined.  Unless specified
856		otherwise, a value change in this file generates a file
857		modified event.
859		  populated
860			1 if the cgroup or its descendants contains any live
861			processes; otherwise, 0.
863	  cgroup.max.descendants
864		A read-write single value files.  The default is "max".
866		Maximum allowed number of descent cgroups.
867		If the actual number of descendants is equal or larger,
868		an attempt to create a new cgroup in the hierarchy will fail.
870	  cgroup.max.depth
871		A read-write single value files.  The default is "max".
873		Maximum allowed descent depth below the current cgroup.
874		If the actual descent depth is equal or larger,
875		an attempt to create a new child cgroup will fail.
877	  cgroup.stat
878		A read-only flat-keyed file with the following entries:
880		  nr_descendants
881			Total number of visible descendant cgroups.
883		  nr_dying_descendants
884			Total number of dying descendant cgroups. A cgroup becomes
885			dying after being deleted by a user. The cgroup will remain
886			in dying state for some time undefined time (which can depend
887			on system load) before being completely destroyed.
889			A process can't enter a dying cgroup under any circumstances,
890			a dying cgroup can't revive.
892			A dying cgroup can consume system resources not exceeding
893			limits, which were active at the moment of cgroup deletion.
896	Controllers
897	===========
899	CPU
900	---
902	The "cpu" controllers regulates distribution of CPU cycles.  This
903	controller implements weight and absolute bandwidth limit models for
904	normal scheduling policy and absolute bandwidth allocation model for
905	realtime scheduling policy.
907	WARNING: cgroup2 doesn't yet support control of realtime processes and
908	the cpu controller can only be enabled when all RT processes are in
909	the root cgroup.  Be aware that system management software may already
910	have placed RT processes into nonroot cgroups during the system boot
911	process, and these processes may need to be moved to the root cgroup
912	before the cpu controller can be enabled.
915	CPU Interface Files
916	~~~~~~~~~~~~~~~~~~~
918	All time durations are in microseconds.
920	  cpu.stat
921		A read-only flat-keyed file which exists on non-root cgroups.
922		This file exists whether the controller is enabled or not.
924		It always reports the following three stats:
926		- usage_usec
927		- user_usec
928		- system_usec
930		and the following three when the controller is enabled:
932		- nr_periods
933		- nr_throttled
934		- throttled_usec
936	  cpu.weight
937		A read-write single value file which exists on non-root
938		cgroups.  The default is "100".
940		The weight in the range [1, 10000].
942	  cpu.weight.nice
943		A read-write single value file which exists on non-root
944		cgroups.  The default is "0".
946		The nice value is in the range [-20, 19].
948		This interface file is an alternative interface for
949		"cpu.weight" and allows reading and setting weight using the
950		same values used by nice(2).  Because the range is smaller and
951		granularity is coarser for the nice values, the read value is
952		the closest approximation of the current weight.
954	  cpu.max
955		A read-write two value file which exists on non-root cgroups.
956		The default is "max 100000".
958		The maximum bandwidth limit.  It's in the following format::
960		  $MAX $PERIOD
962		which indicates that the group may consume upto $MAX in each
963		$PERIOD duration.  "max" for $MAX indicates no limit.  If only
964		one number is written, $MAX is updated.
967	Memory
968	------
970	The "memory" controller regulates distribution of memory.  Memory is
971	stateful and implements both limit and protection models.  Due to the
972	intertwining between memory usage and reclaim pressure and the
973	stateful nature of memory, the distribution model is relatively
974	complex.
976	While not completely water-tight, all major memory usages by a given
977	cgroup are tracked so that the total memory consumption can be
978	accounted and controlled to a reasonable extent.  Currently, the
979	following types of memory usages are tracked.
981	- Userland memory - page cache and anonymous memory.
983	- Kernel data structures such as dentries and inodes.
985	- TCP socket buffers.
987	The above list may expand in the future for better coverage.
990	Memory Interface Files
991	~~~~~~~~~~~~~~~~~~~~~~
993	All memory amounts are in bytes.  If a value which is not aligned to
994	PAGE_SIZE is written, the value may be rounded up to the closest
995	PAGE_SIZE multiple when read back.
997	  memory.current
998		A read-only single value file which exists on non-root
999		cgroups.
1001		The total amount of memory currently being used by the cgroup
1002		and its descendants.
1004	  memory.low
1005		A read-write single value file which exists on non-root
1006		cgroups.  The default is "0".
1008		Best-effort memory protection.  If the memory usages of a
1009		cgroup and all its ancestors are below their low boundaries,
1010		the cgroup's memory won't be reclaimed unless memory can be
1011		reclaimed from unprotected cgroups.
1013		Putting more memory than generally available under this
1014		protection is discouraged.
1016	  memory.high
1017		A read-write single value file which exists on non-root
1018		cgroups.  The default is "max".
1020		Memory usage throttle limit.  This is the main mechanism to
1021		control memory usage of a cgroup.  If a cgroup's usage goes
1022		over the high boundary, the processes of the cgroup are
1023		throttled and put under heavy reclaim pressure.
1025		Going over the high limit never invokes the OOM killer and
1026		under extreme conditions the limit may be breached.
1028	  memory.max
1029		A read-write single value file which exists on non-root
1030		cgroups.  The default is "max".
1032		Memory usage hard limit.  This is the final protection
1033		mechanism.  If a cgroup's memory usage reaches this limit and
1034		can't be reduced, the OOM killer is invoked in the cgroup.
1035		Under certain circumstances, the usage may go over the limit
1036		temporarily.
1038		This is the ultimate protection mechanism.  As long as the
1039		high limit is used and monitored properly, this limit's
1040		utility is limited to providing the final safety net.
1042	  memory.events
1043		A read-only flat-keyed file which exists on non-root cgroups.
1044		The following entries are defined.  Unless specified
1045		otherwise, a value change in this file generates a file
1046		modified event.
1048		  low
1049			The number of times the cgroup is reclaimed due to
1050			high memory pressure even though its usage is under
1051			the low boundary.  This usually indicates that the low
1052			boundary is over-committed.
1054		  high
1055			The number of times processes of the cgroup are
1056			throttled and routed to perform direct memory reclaim
1057			because the high memory boundary was exceeded.  For a
1058			cgroup whose memory usage is capped by the high limit
1059			rather than global memory pressure, this event's
1060			occurrences are expected.
1062		  max
1063			The number of times the cgroup's memory usage was
1064			about to go over the max boundary.  If direct reclaim
1065			fails to bring it down, the cgroup goes to OOM state.
1067		  oom
1068			The number of time the cgroup's memory usage was
1069			reached the limit and allocation was about to fail.
1071			Depending on context result could be invocation of OOM
1072			killer and retrying allocation or failing allocation.
1074			Failed allocation in its turn could be returned into
1075			userspace as -ENOMEM or silently ignored in cases like
1076			disk readahead.  For now OOM in memory cgroup kills
1077			tasks iff shortage has happened inside page fault.
1079		  oom_kill
1080			The number of processes belonging to this cgroup
1081			killed by any kind of OOM killer.
1083	  memory.stat
1084		A read-only flat-keyed file which exists on non-root cgroups.
1086		This breaks down the cgroup's memory footprint into different
1087		types of memory, type-specific details, and other information
1088		on the state and past events of the memory management system.
1090		All memory amounts are in bytes.
1092		The entries are ordered to be human readable, and new entries
1093		can show up in the middle. Don't rely on items remaining in a
1094		fixed position; use the keys to look up specific values!
1096		  anon
1097			Amount of memory used in anonymous mappings such as
1098			brk(), sbrk(), and mmap(MAP_ANONYMOUS)
1100		  file
1101			Amount of memory used to cache filesystem data,
1102			including tmpfs and shared memory.
1104		  kernel_stack
1105			Amount of memory allocated to kernel stacks.
1107		  slab
1108			Amount of memory used for storing in-kernel data
1109			structures.
1111		  sock
1112			Amount of memory used in network transmission buffers
1114		  shmem
1115			Amount of cached filesystem data that is swap-backed,
1116			such as tmpfs, shm segments, shared anonymous mmap()s
1118		  file_mapped
1119			Amount of cached filesystem data mapped with mmap()
1121		  file_dirty
1122			Amount of cached filesystem data that was modified but
1123			not yet written back to disk
1125		  file_writeback
1126			Amount of cached filesystem data that was modified and
1127			is currently being written back to disk
1129		  inactive_anon, active_anon, inactive_file, active_file, unevictable
1130			Amount of memory, swap-backed and filesystem-backed,
1131			on the internal memory management lists used by the
1132			page reclaim algorithm
1134		  slab_reclaimable
1135			Part of "slab" that might be reclaimed, such as
1136			dentries and inodes.
1138		  slab_unreclaimable
1139			Part of "slab" that cannot be reclaimed on memory
1140			pressure.
1142		  pgfault
1143			Total number of page faults incurred
1145		  pgmajfault
1146			Number of major page faults incurred
1148		  workingset_refault
1150			Number of refaults of previously evicted pages
1152		  workingset_activate
1154			Number of refaulted pages that were immediately activated
1156		  workingset_nodereclaim
1158			Number of times a shadow node has been reclaimed
1160		  pgrefill
1162			Amount of scanned pages (in an active LRU list)
1164		  pgscan
1166			Amount of scanned pages (in an inactive LRU list)
1168		  pgsteal
1170			Amount of reclaimed pages
1172		  pgactivate
1174			Amount of pages moved to the active LRU list
1176		  pgdeactivate
1178			Amount of pages moved to the inactive LRU lis
1180		  pglazyfree
1182			Amount of pages postponed to be freed under memory pressure
1184		  pglazyfreed
1186			Amount of reclaimed lazyfree pages
1188	  memory.swap.current
1189		A read-only single value file which exists on non-root
1190		cgroups.
1192		The total amount of swap currently being used by the cgroup
1193		and its descendants.
1195	  memory.swap.max
1196		A read-write single value file which exists on non-root
1197		cgroups.  The default is "max".
1199		Swap usage hard limit.  If a cgroup's swap usage reaches this
1200		limit, anonymous memory of the cgroup will not be swapped out.
1203	Usage Guidelines
1204	~~~~~~~~~~~~~~~~
1206	"memory.high" is the main mechanism to control memory usage.
1207	Over-committing on high limit (sum of high limits > available memory)
1208	and letting global memory pressure to distribute memory according to
1209	usage is a viable strategy.
1211	Because breach of the high limit doesn't trigger the OOM killer but
1212	throttles the offending cgroup, a management agent has ample
1213	opportunities to monitor and take appropriate actions such as granting
1214	more memory or terminating the workload.
1216	Determining whether a cgroup has enough memory is not trivial as
1217	memory usage doesn't indicate whether the workload can benefit from
1218	more memory.  For example, a workload which writes data received from
1219	network to a file can use all available memory but can also operate as
1220	performant with a small amount of memory.  A measure of memory
1221	pressure - how much the workload is being impacted due to lack of
1222	memory - is necessary to determine whether a workload needs more
1223	memory; unfortunately, memory pressure monitoring mechanism isn't
1224	implemented yet.
1227	Memory Ownership
1228	~~~~~~~~~~~~~~~~
1230	A memory area is charged to the cgroup which instantiated it and stays
1231	charged to the cgroup until the area is released.  Migrating a process
1232	to a different cgroup doesn't move the memory usages that it
1233	instantiated while in the previous cgroup to the new cgroup.
1235	A memory area may be used by processes belonging to different cgroups.
1236	To which cgroup the area will be charged is in-deterministic; however,
1237	over time, the memory area is likely to end up in a cgroup which has
1238	enough memory allowance to avoid high reclaim pressure.
1240	If a cgroup sweeps a considerable amount of memory which is expected
1241	to be accessed repeatedly by other cgroups, it may make sense to use
1242	POSIX_FADV_DONTNEED to relinquish the ownership of memory areas
1243	belonging to the affected files to ensure correct memory ownership.
1246	IO
1247	--
1249	The "io" controller regulates the distribution of IO resources.  This
1250	controller implements both weight based and absolute bandwidth or IOPS
1251	limit distribution; however, weight based distribution is available
1252	only if cfq-iosched is in use and neither scheme is available for
1253	blk-mq devices.
1256	IO Interface Files
1257	~~~~~~~~~~~~~~~~~~
1259	  io.stat
1260		A read-only nested-keyed file which exists on non-root
1261		cgroups.
1263		Lines are keyed by $MAJ:$MIN device numbers and not ordered.
1264		The following nested keys are defined.
1266		  ======	===================
1267		  rbytes	Bytes read
1268		  wbytes	Bytes written
1269		  rios		Number of read IOs
1270		  wios		Number of write IOs
1271		  ======	===================
1273		An example read output follows:
1275		  8:16 rbytes=1459200 wbytes=314773504 rios=192 wios=353
1276		  8:0 rbytes=90430464 wbytes=299008000 rios=8950 wios=1252
1278	  io.weight
1279		A read-write flat-keyed file which exists on non-root cgroups.
1280		The default is "default 100".
1282		The first line is the default weight applied to devices
1283		without specific override.  The rest are overrides keyed by
1284		$MAJ:$MIN device numbers and not ordered.  The weights are in
1285		the range [1, 10000] and specifies the relative amount IO time
1286		the cgroup can use in relation to its siblings.
1288		The default weight can be updated by writing either "default
1289		$WEIGHT" or simply "$WEIGHT".  Overrides can be set by writing
1290		"$MAJ:$MIN $WEIGHT" and unset by writing "$MAJ:$MIN default".
1292		An example read output follows::
1294		  default 100
1295		  8:16 200
1296		  8:0 50
1298	  io.max
1299		A read-write nested-keyed file which exists on non-root
1300		cgroups.
1302		BPS and IOPS based IO limit.  Lines are keyed by $MAJ:$MIN
1303		device numbers and not ordered.  The following nested keys are
1304		defined.
1306		  =====		==================================
1307		  rbps		Max read bytes per second
1308		  wbps		Max write bytes per second
1309		  riops		Max read IO operations per second
1310		  wiops		Max write IO operations per second
1311		  =====		==================================
1313		When writing, any number of nested key-value pairs can be
1314		specified in any order.  "max" can be specified as the value
1315		to remove a specific limit.  If the same key is specified
1316		multiple times, the outcome is undefined.
1318		BPS and IOPS are measured in each IO direction and IOs are
1319		delayed if limit is reached.  Temporary bursts are allowed.
1321		Setting read limit at 2M BPS and write at 120 IOPS for 8:16::
1323		  echo "8:16 rbps=2097152 wiops=120" > io.max
1325		Reading returns the following::
1327		  8:16 rbps=2097152 wbps=max riops=max wiops=120
1329		Write IOPS limit can be removed by writing the following::
1331		  echo "8:16 wiops=max" > io.max
1333		Reading now returns the following::
1335		  8:16 rbps=2097152 wbps=max riops=max wiops=max
1338	Writeback
1339	~~~~~~~~~
1341	Page cache is dirtied through buffered writes and shared mmaps and
1342	written asynchronously to the backing filesystem by the writeback
1343	mechanism.  Writeback sits between the memory and IO domains and
1344	regulates the proportion of dirty memory by balancing dirtying and
1345	write IOs.
1347	The io controller, in conjunction with the memory controller,
1348	implements control of page cache writeback IOs.  The memory controller
1349	defines the memory domain that dirty memory ratio is calculated and
1350	maintained for and the io controller defines the io domain which
1351	writes out dirty pages for the memory domain.  Both system-wide and
1352	per-cgroup dirty memory states are examined and the more restrictive
1353	of the two is enforced.
1355	cgroup writeback requires explicit support from the underlying
1356	filesystem.  Currently, cgroup writeback is implemented on ext2, ext4
1357	and btrfs.  On other filesystems, all writeback IOs are attributed to
1358	the root cgroup.
1360	There are inherent differences in memory and writeback management
1361	which affects how cgroup ownership is tracked.  Memory is tracked per
1362	page while writeback per inode.  For the purpose of writeback, an
1363	inode is assigned to a cgroup and all IO requests to write dirty pages
1364	from the inode are attributed to that cgroup.
1366	As cgroup ownership for memory is tracked per page, there can be pages
1367	which are associated with different cgroups than the one the inode is
1368	associated with.  These are called foreign pages.  The writeback
1369	constantly keeps track of foreign pages and, if a particular foreign
1370	cgroup becomes the majority over a certain period of time, switches
1371	the ownership of the inode to that cgroup.
1373	While this model is enough for most use cases where a given inode is
1374	mostly dirtied by a single cgroup even when the main writing cgroup
1375	changes over time, use cases where multiple cgroups write to a single
1376	inode simultaneously are not supported well.  In such circumstances, a
1377	significant portion of IOs are likely to be attributed incorrectly.
1378	As memory controller assigns page ownership on the first use and
1379	doesn't update it until the page is released, even if writeback
1380	strictly follows page ownership, multiple cgroups dirtying overlapping
1381	areas wouldn't work as expected.  It's recommended to avoid such usage
1382	patterns.
1384	The sysctl knobs which affect writeback behavior are applied to cgroup
1385	writeback as follows.
1387	  vm.dirty_background_ratio, vm.dirty_ratio
1388		These ratios apply the same to cgroup writeback with the
1389		amount of available memory capped by limits imposed by the
1390		memory controller and system-wide clean memory.
1392	  vm.dirty_background_bytes, vm.dirty_bytes
1393		For cgroup writeback, this is calculated into ratio against
1394		total available memory and applied the same way as
1395		vm.dirty[_background]_ratio.
1398	PID
1399	---
1401	The process number controller is used to allow a cgroup to stop any
1402	new tasks from being fork()'d or clone()'d after a specified limit is
1403	reached.
1405	The number of tasks in a cgroup can be exhausted in ways which other
1406	controllers cannot prevent, thus warranting its own controller.  For
1407	example, a fork bomb is likely to exhaust the number of tasks before
1408	hitting memory restrictions.
1410	Note that PIDs used in this controller refer to TIDs, process IDs as
1411	used by the kernel.
1414	PID Interface Files
1415	~~~~~~~~~~~~~~~~~~~
1417	  pids.max
1418		A read-write single value file which exists on non-root
1419		cgroups.  The default is "max".
1421		Hard limit of number of processes.
1423	  pids.current
1424		A read-only single value file which exists on all cgroups.
1426		The number of processes currently in the cgroup and its
1427		descendants.
1429	Organisational operations are not blocked by cgroup policies, so it is
1430	possible to have pids.current > pids.max.  This can be done by either
1431	setting the limit to be smaller than pids.current, or attaching enough
1432	processes to the cgroup such that pids.current is larger than
1433	pids.max.  However, it is not possible to violate a cgroup PID policy
1434	through fork() or clone(). These will return -EAGAIN if the creation
1435	of a new process would cause a cgroup policy to be violated.
1438	Device controller
1439	-----------------
1441	Device controller manages access to device files. It includes both
1442	creation of new device files (using mknod), and access to the
1443	existing device files.
1445	Cgroup v2 device controller has no interface files and is implemented
1446	on top of cgroup BPF. To control access to device files, a user may
1447	create bpf programs of the BPF_CGROUP_DEVICE type and attach them
1448	to cgroups. On an attempt to access a device file, corresponding
1449	BPF programs will be executed, and depending on the return value
1450	the attempt will succeed or fail with -EPERM.
1452	A BPF_CGROUP_DEVICE program takes a pointer to the bpf_cgroup_dev_ctx
1453	structure, which describes the device access attempt: access type
1454	(mknod/read/write) and device (type, major and minor numbers).
1455	If the program returns 0, the attempt fails with -EPERM, otherwise
1456	it succeeds.
1458	An example of BPF_CGROUP_DEVICE program may be found in the kernel
1459	source tree in the tools/testing/selftests/bpf/dev_cgroup.c file.
1462	RDMA
1463	----
1465	The "rdma" controller regulates the distribution and accounting of
1466	of RDMA resources.
1468	RDMA Interface Files
1469	~~~~~~~~~~~~~~~~~~~~
1471	  rdma.max
1472		A readwrite nested-keyed file that exists for all the cgroups
1473		except root that describes current configured resource limit
1474		for a RDMA/IB device.
1476		Lines are keyed by device name and are not ordered.
1477		Each line contains space separated resource name and its configured
1478		limit that can be distributed.
1480		The following nested keys are defined.
1482		  ==========	=============================
1483		  hca_handle	Maximum number of HCA Handles
1484		  hca_object 	Maximum number of HCA Objects
1485		  ==========	=============================
1487		An example for mlx4 and ocrdma device follows::
1489		  mlx4_0 hca_handle=2 hca_object=2000
1490		  ocrdma1 hca_handle=3 hca_object=max
1492	  rdma.current
1493		A read-only file that describes current resource usage.
1494		It exists for all the cgroup except root.
1496		An example for mlx4 and ocrdma device follows::
1498		  mlx4_0 hca_handle=1 hca_object=20
1499		  ocrdma1 hca_handle=1 hca_object=23
1502	Misc
1503	----
1505	perf_event
1506	~~~~~~~~~~
1508	perf_event controller, if not mounted on a legacy hierarchy, is
1509	automatically enabled on the v2 hierarchy so that perf events can
1510	always be filtered by cgroup v2 path.  The controller can still be
1511	moved to a legacy hierarchy after v2 hierarchy is populated.
1514	Non-normative information
1515	-------------------------
1517	This section contains information that isn't considered to be a part of
1518	the stable kernel API and so is subject to change.
1521	CPU controller root cgroup process behaviour
1522	~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
1524	When distributing CPU cycles in the root cgroup each thread in this
1525	cgroup is treated as if it was hosted in a separate child cgroup of the
1526	root cgroup. This child cgroup weight is dependent on its thread nice
1527	level.
1529	For details of this mapping see sched_prio_to_weight array in
1530	kernel/sched/core.c file (values from this array should be scaled
1531	appropriately so the neutral - nice 0 - value is 100 instead of 1024).
1534	IO controller root cgroup process behaviour
1535	~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
1537	Root cgroup processes are hosted in an implicit leaf child node.
1538	When distributing IO resources this implicit child node is taken into
1539	account as if it was a normal child cgroup of the root cgroup with a
1540	weight value of 200.
1543	Namespace
1544	=========
1546	Basics
1547	------
1549	cgroup namespace provides a mechanism to virtualize the view of the
1550	"/proc/$PID/cgroup" file and cgroup mounts.  The CLONE_NEWCGROUP clone
1551	flag can be used with clone(2) and unshare(2) to create a new cgroup
1552	namespace.  The process running inside the cgroup namespace will have
1553	its "/proc/$PID/cgroup" output restricted to cgroupns root.  The
1554	cgroupns root is the cgroup of the process at the time of creation of
1555	the cgroup namespace.
1557	Without cgroup namespace, the "/proc/$PID/cgroup" file shows the
1558	complete path of the cgroup of a process.  In a container setup where
1559	a set of cgroups and namespaces are intended to isolate processes the
1560	"/proc/$PID/cgroup" file may leak potential system level information
1561	to the isolated processes.  For Example::
1563	  # cat /proc/self/cgroup
1564	  0::/batchjobs/container_id1
1566	The path '/batchjobs/container_id1' can be considered as system-data
1567	and undesirable to expose to the isolated processes.  cgroup namespace
1568	can be used to restrict visibility of this path.  For example, before
1569	creating a cgroup namespace, one would see::
1571	  # ls -l /proc/self/ns/cgroup
1572	  lrwxrwxrwx 1 root root 0 2014-07-15 10:37 /proc/self/ns/cgroup -> cgroup:[4026531835]
1573	  # cat /proc/self/cgroup
1574	  0::/batchjobs/container_id1
1576	After unsharing a new namespace, the view changes::
1578	  # ls -l /proc/self/ns/cgroup
1579	  lrwxrwxrwx 1 root root 0 2014-07-15 10:35 /proc/self/ns/cgroup -> cgroup:[4026532183]
1580	  # cat /proc/self/cgroup
1581	  0::/
1583	When some thread from a multi-threaded process unshares its cgroup
1584	namespace, the new cgroupns gets applied to the entire process (all
1585	the threads).  This is natural for the v2 hierarchy; however, for the
1586	legacy hierarchies, this may be unexpected.
1588	A cgroup namespace is alive as long as there are processes inside or
1589	mounts pinning it.  When the last usage goes away, the cgroup
1590	namespace is destroyed.  The cgroupns root and the actual cgroups
1591	remain.
1594	The Root and Views
1595	------------------
1597	The 'cgroupns root' for a cgroup namespace is the cgroup in which the
1598	process calling unshare(2) is running.  For example, if a process in
1599	/batchjobs/container_id1 cgroup calls unshare, cgroup
1600	/batchjobs/container_id1 becomes the cgroupns root.  For the
1601	init_cgroup_ns, this is the real root ('/') cgroup.
1603	The cgroupns root cgroup does not change even if the namespace creator
1604	process later moves to a different cgroup::
1606	  # ~/unshare -c # unshare cgroupns in some cgroup
1607	  # cat /proc/self/cgroup
1608	  0::/
1609	  # mkdir sub_cgrp_1
1610	  # echo 0 > sub_cgrp_1/cgroup.procs
1611	  # cat /proc/self/cgroup
1612	  0::/sub_cgrp_1
1614	Each process gets its namespace-specific view of "/proc/$PID/cgroup"
1616	Processes running inside the cgroup namespace will be able to see
1617	cgroup paths (in /proc/self/cgroup) only inside their root cgroup.
1618	From within an unshared cgroupns::
1620	  # sleep 100000 &
1621	  [1] 7353
1622	  # echo 7353 > sub_cgrp_1/cgroup.procs
1623	  # cat /proc/7353/cgroup
1624	  0::/sub_cgrp_1
1626	From the initial cgroup namespace, the real cgroup path will be
1627	visible::
1629	  $ cat /proc/7353/cgroup
1630	  0::/batchjobs/container_id1/sub_cgrp_1
1632	From a sibling cgroup namespace (that is, a namespace rooted at a
1633	different cgroup), the cgroup path relative to its own cgroup
1634	namespace root will be shown.  For instance, if PID 7353's cgroup
1635	namespace root is at '/batchjobs/container_id2', then it will see::
1637	  # cat /proc/7353/cgroup
1638	  0::/../container_id2/sub_cgrp_1
1640	Note that the relative path always starts with '/' to indicate that
1641	its relative to the cgroup namespace root of the caller.
1644	Migration and setns(2)
1645	----------------------
1647	Processes inside a cgroup namespace can move into and out of the
1648	namespace root if they have proper access to external cgroups.  For
1649	example, from inside a namespace with cgroupns root at
1650	/batchjobs/container_id1, and assuming that the global hierarchy is
1651	still accessible inside cgroupns::
1653	  # cat /proc/7353/cgroup
1654	  0::/sub_cgrp_1
1655	  # echo 7353 > batchjobs/container_id2/cgroup.procs
1656	  # cat /proc/7353/cgroup
1657	  0::/../container_id2
1659	Note that this kind of setup is not encouraged.  A task inside cgroup
1660	namespace should only be exposed to its own cgroupns hierarchy.
1662	setns(2) to another cgroup namespace is allowed when:
1664	(a) the process has CAP_SYS_ADMIN against its current user namespace
1665	(b) the process has CAP_SYS_ADMIN against the target cgroup
1666	    namespace's userns
1668	No implicit cgroup changes happen with attaching to another cgroup
1669	namespace.  It is expected that the someone moves the attaching
1670	process under the target cgroup namespace root.
1673	Interaction with Other Namespaces
1674	---------------------------------
1676	Namespace specific cgroup hierarchy can be mounted by a process
1677	running inside a non-init cgroup namespace::
1679	  # mount -t cgroup2 none $MOUNT_POINT
1681	This will mount the unified cgroup hierarchy with cgroupns root as the
1682	filesystem root.  The process needs CAP_SYS_ADMIN against its user and
1683	mount namespaces.
1685	The virtualization of /proc/self/cgroup file combined with restricting
1686	the view of cgroup hierarchy by namespace-private cgroupfs mount
1687	provides a properly isolated cgroup view inside the container.
1690	Information on Kernel Programming
1691	=================================
1693	This section contains kernel programming information in the areas
1694	where interacting with cgroup is necessary.  cgroup core and
1695	controllers are not covered.
1698	Filesystem Support for Writeback
1699	--------------------------------
1701	A filesystem can support cgroup writeback by updating
1702	address_space_operations->writepage[s]() to annotate bio's using the
1703	following two functions.
1705	  wbc_init_bio(@wbc, @bio)
1706		Should be called for each bio carrying writeback data and
1707		associates the bio with the inode's owner cgroup.  Can be
1708		called anytime between bio allocation and submission.
1710	  wbc_account_io(@wbc, @page, @bytes)
1711		Should be called for each data segment being written out.
1712		While this function doesn't care exactly when it's called
1713		during the writeback session, it's the easiest and most
1714		natural to call it as data segments are added to a bio.
1716	With writeback bio's annotated, cgroup support can be enabled per
1717	super_block by setting SB_I_CGROUPWB in ->s_iflags.  This allows for
1718	selective disabling of cgroup writeback support which is helpful when
1719	certain filesystem features, e.g. journaled data mode, are
1720	incompatible.
1722	wbc_init_bio() binds the specified bio to its cgroup.  Depending on
1723	the configuration, the bio may be executed at a lower priority and if
1724	the writeback session is holding shared resources, e.g. a journal
1725	entry, may lead to priority inversion.  There is no one easy solution
1726	for the problem.  Filesystems can try to work around specific problem
1727	cases by skipping wbc_init_bio() or using bio_associate_blkcg()
1728	directly.
1731	Deprecated v1 Core Features
1732	===========================
1734	- Multiple hierarchies including named ones are not supported.
1736	- All v1 mount options are not supported.
1738	- The "tasks" file is removed and "cgroup.procs" is not sorted.
1740	- "cgroup.clone_children" is removed.
1742	- /proc/cgroups is meaningless for v2.  Use "cgroup.controllers" file
1743	  at the root instead.
1746	Issues with v1 and Rationales for v2
1747	====================================
1749	Multiple Hierarchies
1750	--------------------
1752	cgroup v1 allowed an arbitrary number of hierarchies and each
1753	hierarchy could host any number of controllers.  While this seemed to
1754	provide a high level of flexibility, it wasn't useful in practice.
1756	For example, as there is only one instance of each controller, utility
1757	type controllers such as freezer which can be useful in all
1758	hierarchies could only be used in one.  The issue is exacerbated by
1759	the fact that controllers couldn't be moved to another hierarchy once
1760	hierarchies were populated.  Another issue was that all controllers
1761	bound to a hierarchy were forced to have exactly the same view of the
1762	hierarchy.  It wasn't possible to vary the granularity depending on
1763	the specific controller.
1765	In practice, these issues heavily limited which controllers could be
1766	put on the same hierarchy and most configurations resorted to putting
1767	each controller on its own hierarchy.  Only closely related ones, such
1768	as the cpu and cpuacct controllers, made sense to be put on the same
1769	hierarchy.  This often meant that userland ended up managing multiple
1770	similar hierarchies repeating the same steps on each hierarchy
1771	whenever a hierarchy management operation was necessary.
1773	Furthermore, support for multiple hierarchies came at a steep cost.
1774	It greatly complicated cgroup core implementation but more importantly
1775	the support for multiple hierarchies restricted how cgroup could be
1776	used in general and what controllers was able to do.
1778	There was no limit on how many hierarchies there might be, which meant
1779	that a thread's cgroup membership couldn't be described in finite
1780	length.  The key might contain any number of entries and was unlimited
1781	in length, which made it highly awkward to manipulate and led to
1782	addition of controllers which existed only to identify membership,
1783	which in turn exacerbated the original problem of proliferating number
1784	of hierarchies.
1786	Also, as a controller couldn't have any expectation regarding the
1787	topologies of hierarchies other controllers might be on, each
1788	controller had to assume that all other controllers were attached to
1789	completely orthogonal hierarchies.  This made it impossible, or at
1790	least very cumbersome, for controllers to cooperate with each other.
1792	In most use cases, putting controllers on hierarchies which are
1793	completely orthogonal to each other isn't necessary.  What usually is
1794	called for is the ability to have differing levels of granularity
1795	depending on the specific controller.  In other words, hierarchy may
1796	be collapsed from leaf towards root when viewed from specific
1797	controllers.  For example, a given configuration might not care about
1798	how memory is distributed beyond a certain level while still wanting
1799	to control how CPU cycles are distributed.
1802	Thread Granularity
1803	------------------
1805	cgroup v1 allowed threads of a process to belong to different cgroups.
1806	This didn't make sense for some controllers and those controllers
1807	ended up implementing different ways to ignore such situations but
1808	much more importantly it blurred the line between API exposed to
1809	individual applications and system management interface.
1811	Generally, in-process knowledge is available only to the process
1812	itself; thus, unlike service-level organization of processes,
1813	categorizing threads of a process requires active participation from
1814	the application which owns the target process.
1816	cgroup v1 had an ambiguously defined delegation model which got abused
1817	in combination with thread granularity.  cgroups were delegated to
1818	individual applications so that they can create and manage their own
1819	sub-hierarchies and control resource distributions along them.  This
1820	effectively raised cgroup to the status of a syscall-like API exposed
1821	to lay programs.
1823	First of all, cgroup has a fundamentally inadequate interface to be
1824	exposed this way.  For a process to access its own knobs, it has to
1825	extract the path on the target hierarchy from /proc/self/cgroup,
1826	construct the path by appending the name of the knob to the path, open
1827	and then read and/or write to it.  This is not only extremely clunky
1828	and unusual but also inherently racy.  There is no conventional way to
1829	define transaction across the required steps and nothing can guarantee
1830	that the process would actually be operating on its own sub-hierarchy.
1832	cgroup controllers implemented a number of knobs which would never be
1833	accepted as public APIs because they were just adding control knobs to
1834	system-management pseudo filesystem.  cgroup ended up with interface
1835	knobs which were not properly abstracted or refined and directly
1836	revealed kernel internal details.  These knobs got exposed to
1837	individual applications through the ill-defined delegation mechanism
1838	effectively abusing cgroup as a shortcut to implementing public APIs
1839	without going through the required scrutiny.
1841	This was painful for both userland and kernel.  Userland ended up with
1842	misbehaving and poorly abstracted interfaces and kernel exposing and
1843	locked into constructs inadvertently.
1846	Competition Between Inner Nodes and Threads
1847	-------------------------------------------
1849	cgroup v1 allowed threads to be in any cgroups which created an
1850	interesting problem where threads belonging to a parent cgroup and its
1851	children cgroups competed for resources.  This was nasty as two
1852	different types of entities competed and there was no obvious way to
1853	settle it.  Different controllers did different things.
1855	The cpu controller considered threads and cgroups as equivalents and
1856	mapped nice levels to cgroup weights.  This worked for some cases but
1857	fell flat when children wanted to be allocated specific ratios of CPU
1858	cycles and the number of internal threads fluctuated - the ratios
1859	constantly changed as the number of competing entities fluctuated.
1860	There also were other issues.  The mapping from nice level to weight
1861	wasn't obvious or universal, and there were various other knobs which
1862	simply weren't available for threads.
1864	The io controller implicitly created a hidden leaf node for each
1865	cgroup to host the threads.  The hidden leaf had its own copies of all
1866	the knobs with ``leaf_`` prefixed.  While this allowed equivalent
1867	control over internal threads, it was with serious drawbacks.  It
1868	always added an extra layer of nesting which wouldn't be necessary
1869	otherwise, made the interface messy and significantly complicated the
1870	implementation.
1872	The memory controller didn't have a way to control what happened
1873	between internal tasks and child cgroups and the behavior was not
1874	clearly defined.  There were attempts to add ad-hoc behaviors and
1875	knobs to tailor the behavior to specific workloads which would have
1876	led to problems extremely difficult to resolve in the long term.
1878	Multiple controllers struggled with internal tasks and came up with
1879	different ways to deal with it; unfortunately, all the approaches were
1880	severely flawed and, furthermore, the widely different behaviors
1881	made cgroup as a whole highly inconsistent.
1883	This clearly is a problem which needs to be addressed from cgroup core
1884	in a uniform way.
1887	Other Interface Issues
1888	----------------------
1890	cgroup v1 grew without oversight and developed a large number of
1891	idiosyncrasies and inconsistencies.  One issue on the cgroup core side
1892	was how an empty cgroup was notified - a userland helper binary was
1893	forked and executed for each event.  The event delivery wasn't
1894	recursive or delegatable.  The limitations of the mechanism also led
1895	to in-kernel event delivery filtering mechanism further complicating
1896	the interface.
1898	Controller interfaces were problematic too.  An extreme example is
1899	controllers completely ignoring hierarchical organization and treating
1900	all cgroups as if they were all located directly under the root
1901	cgroup.  Some controllers exposed a large amount of inconsistent
1902	implementation details to userland.
1904	There also was no consistency across controllers.  When a new cgroup
1905	was created, some controllers defaulted to not imposing extra
1906	restrictions while others disallowed any resource usage until
1907	explicitly configured.  Configuration knobs for the same type of
1908	control used widely differing naming schemes and formats.  Statistics
1909	and information knobs were named arbitrarily and used different
1910	formats and units even in the same controller.
1912	cgroup v2 establishes common conventions where appropriate and updates
1913	controllers so that they expose minimal and consistent interfaces.
1916	Controller Issues and Remedies
1917	------------------------------
1919	Memory
1920	~~~~~~
1922	The original lower boundary, the soft limit, is defined as a limit
1923	that is per default unset.  As a result, the set of cgroups that
1924	global reclaim prefers is opt-in, rather than opt-out.  The costs for
1925	optimizing these mostly negative lookups are so high that the
1926	implementation, despite its enormous size, does not even provide the
1927	basic desirable behavior.  First off, the soft limit has no
1928	hierarchical meaning.  All configured groups are organized in a global
1929	rbtree and treated like equal peers, regardless where they are located
1930	in the hierarchy.  This makes subtree delegation impossible.  Second,
1931	the soft limit reclaim pass is so aggressive that it not just
1932	introduces high allocation latencies into the system, but also impacts
1933	system performance due to overreclaim, to the point where the feature
1934	becomes self-defeating.
1936	The memory.low boundary on the other hand is a top-down allocated
1937	reserve.  A cgroup enjoys reclaim protection when it and all its
1938	ancestors are below their low boundaries, which makes delegation of
1939	subtrees possible.  Secondly, new cgroups have no reserve per default
1940	and in the common case most cgroups are eligible for the preferred
1941	reclaim pass.  This allows the new low boundary to be efficiently
1942	implemented with just a minor addition to the generic reclaim code,
1943	without the need for out-of-band data structures and reclaim passes.
1944	Because the generic reclaim code considers all cgroups except for the
1945	ones running low in the preferred first reclaim pass, overreclaim of
1946	individual groups is eliminated as well, resulting in much better
1947	overall workload performance.
1949	The original high boundary, the hard limit, is defined as a strict
1950	limit that can not budge, even if the OOM killer has to be called.
1951	But this generally goes against the goal of making the most out of the
1952	available memory.  The memory consumption of workloads varies during
1953	runtime, and that requires users to overcommit.  But doing that with a
1954	strict upper limit requires either a fairly accurate prediction of the
1955	working set size or adding slack to the limit.  Since working set size
1956	estimation is hard and error prone, and getting it wrong results in
1957	OOM kills, most users tend to err on the side of a looser limit and
1958	end up wasting precious resources.
1960	The memory.high boundary on the other hand can be set much more
1961	conservatively.  When hit, it throttles allocations by forcing them
1962	into direct reclaim to work off the excess, but it never invokes the
1963	OOM killer.  As a result, a high boundary that is chosen too
1964	aggressively will not terminate the processes, but instead it will
1965	lead to gradual performance degradation.  The user can monitor this
1966	and make corrections until the minimal memory footprint that still
1967	gives acceptable performance is found.
1969	In extreme cases, with many concurrent allocations and a complete
1970	breakdown of reclaim progress within the group, the high boundary can
1971	be exceeded.  But even then it's mostly better to satisfy the
1972	allocation from the slack available in other groups or the rest of the
1973	system than killing the group.  Otherwise, memory.max is there to
1974	limit this type of spillover and ultimately contain buggy or even
1975	malicious applications.
1977	Setting the original memory.limit_in_bytes below the current usage was
1978	subject to a race condition, where concurrent charges could cause the
1979	limit setting to fail. memory.max on the other hand will first set the
1980	limit to prevent new charges, and then reclaim and OOM kill until the
1981	new limit is met - or the task writing to memory.max is killed.
1983	The combined memory+swap accounting and limiting is replaced by real
1984	control over swap space.
1986	The main argument for a combined memory+swap facility in the original
1987	cgroup design was that global or parental pressure would always be
1988	able to swap all anonymous memory of a child group, regardless of the
1989	child's own (possibly untrusted) configuration.  However, untrusted
1990	groups can sabotage swapping by other means - such as referencing its
1991	anonymous memory in a tight loop - and an admin can not assume full
1992	swappability when overcommitting untrusted jobs.
1994	For trusted jobs, on the other hand, a combined counter is not an
1995	intuitive userspace interface, and it flies in the face of the idea
1996	that cgroup controllers should account and limit specific physical
1997	resources.  Swap space is a resource like all others in the system,
1998	and that's why unified hierarchy allows distributing it separately.
Hide Line Numbers
About Kernel Documentation Linux Kernel Contact Linux Resources Linux Blog

Information is copyright its respective author. All material is available from the Linux Kernel Source distributed under a GPL License. This page is provided as a free service by mjmwired.net.