Copyright (C) 2015 Serge Hallyn <firstname.lastname@example.org> and Copyright (C) 2016 Michael Kerrisk <email@example.com> %%%LICENSE_START(VERBATIM) Permission is granted to make and distribute verbatim copies of this manual provided the copyright notice and this permission notice are preserved on all copies. Permission is granted to copy and distribute modified versions of this manual under the conditions for verbatim copying, provided that the entire resulting derived work is distributed under t...
NAMEcgroups - Linux control groups
DESCRIPTIONControl cgroups, usually referred to as cgroups, are a Linux kernel feature which allow processes to be organized into hierarchical groups whose usage of various types of resources can then be limited and monitored. The kernel's cgroup interface is provided through a pseudo-filesystem called cgroupfs. Grouping is implemented in the core cgroup kernel code, while resource tracking and limits are implemented in a set of per-resource-type subsystems (memory, CPU, and so on).
TerminologyA cgroup is a collection of processes that are bound to a set of limits or parameters defined via the cgroup filesystem.
A subsystem is a kernel component that modifies the behavior of the processes in a cgroup. Various subsystems have been implemented, making it possible to do things such as limiting the amount of CPU time and memory available to a cgroup, accounting for the CPU time used by a cgroup, and freezing and resuming execution of the processes in a cgroup. Subsystems are sometimes also known as resource controllers (or simply, controllers).
The cgroups for a controller are arranged in a hierarchy. This hierarchy is defined by creating, removing, and renaming subdirectories within the cgroup filesystem. At each level of the hierarchy, attributes (e.g., limits) can be defined. The limits, control, and accounting provided by cgroups generally have effect throughout the subhierarchy underneath the cgroup where the attributes are defined. Thus, for example, the limits placed on a cgroup at a higher level in the hierarchy cannot be exceeded by descendant cgroups.
Cgroups version 1 and version 2The initial release of the cgroups implementation was in Linux 2.6.24. Over time, various cgroup controllers have been added to allow the management of various types of resources. However, the development of these controllers was largely uncoordinated, with the result that many inconsistencies arose between controllers and management of the cgroup hierarchies became rather complex. (A longer description of these problems can be found in the kernel source file Documentation/cgroup-v2.txt.)
Because of the problems with the initial cgroups implementation (cgroups version 1), starting in Linux 3.10, work began on a new, orthogonal implementation to remedy these problems. Initially marked experimental, and hidden behind the -o __DEVEL__sane_behavior mount option, the new version (cgroups version 2) was eventually made official with the release of Linux 4.5. Differences between the two versions are described in the text below.
Although cgroups v2 is intended as a replacement for cgroups v1, the older system continues to exist (and for compatibility reasons is unlikely to be removed). Currently, cgroups v2 implements only a subset of the controllers available in cgroups v1. The two systems are implemented so that both v1 controllers and v2 controllers can be mounted on the same system. Thus, for example, it is possible to use those controllers that are supported under version 2, while also using version 1 controllers where version 2 does not yet support those controllers. The only restriction here is that a controller can't be simultaneously employed in both a cgroups v1 hierarchy and in the cgroups v2 hierarchy.
Cgroups version 1Under cgroups v1, each controller may be mounted against a separate cgroup filesystem that provides its own hierarchical organization of the processes on the system. It is also possible comount multiple (or even all) cgroups v1 controllers against the same cgroup filesystem, meaning that the comounted controllers manage the same hierarchical organization of processes.
For each mounted hierarchy, the directory tree mirrors the control group hierarchy. Each control group is represented by a directory, with each of its child control cgroups represented as a child directory. For instance, /user/joe/1.session represents control group 1.session, which is a child of cgroup joe, which is a child of /user. Under each cgroup directory is a set of files which can be read or written to, reflecting resource limits and a few general cgroup properties.
In addition, in cgroups v1, cgroups can be mounted with no bound controller, in which case they serve only to track processes. (See the discussion of release notification below.) An example of this is the name=systemd cgroup which is used by systemd(1) to track services and user sessions.
Tasks (threads) versus processesIn cgroups v1, a distinction is drawn between processes and tasks. In this view, a process can consist of multiple tasks (more commonly called threads, from a user-space perspective, and called such in the remainder of this man page). In cgroups v1, it is possible to independently manipulate the cgroup memberships of the threads in a process. Because this ability caused certain problems, the ability to independently manipulate the cgroup memberships of the threads in a process has been removed in cgroups v2. Cgroups v2 allows manipulation of cgroup membership only for processes (which has the effect of changing the cgroup membership of all threads in the process).
Mounting v1 controllersThe use of cgroups requires a kernel built with the CONFIG_CGROUP option. In addition, each of the v1 controllers has an associated configuration option that must be set in order to employ that controller.
In order to use a v1 controller, it must be mounted against a cgroup filesystem. The usual place for such mounts is under a tmpfs(5) filesystem mounted at /sys/fs/cgroup. Thus, one might mount the cpu controller as follows:
mount -t cgroup -o cpu none /sys/fs/cgroup/cpu
It is possible to comount multiple controllers against the same hierarchy. For example, here the cpu and cpuacct controllers are comounted against a single hierarchy:
mount -t cgroup -o cpu,cpuacct none /sys/fs/cgroup/cpu,cpuacct
Comounting controllers has the effect that a process is in the same cgroup for all of the comounted controllers. Separately mounting controllers allows a process to be in cgroup /foo1 for one controller while being in /foo2/foo3 for another.
It is possible to comount all v1 controllers against the same hierarchy:
mount -t cgroup -o all cgroup /sys/fs/cgroup
(One can achieve the same result by omitting -o all, since it is the default if no controllers are explicitly specified.)
It is not possible to mount the same controller against multiple cgroup hierarchies. For example, it is not possible to mount both the cpu and cpuacct controllers against one hierarchy, and to mount the cpu controller alone against another hierarchy. It is possible to create multiple mount points with exactly the same set of comounted controllers. However, in this case all that results is multiple mount points providing a view of the same hierarchy.
Note that on many systems, the v1 controllers are automatically mounted under /sys/fs/cgroup; in particular, systemd(1) automatically creates such mount points.
Cgroups version 1 controllersEach of the cgroups version 1 controllers is governed by a kernel configuration option (listed below). Additionally, the availability of the cgroups feature is governed by the CONFIG_CGROUPS kernel configuration option.
- cpu (since Linux 2.6.24; CONFIG_CGROUP_SCHED)
- Cgroups can be guaranteed a minimum number of "CPU shares" when a system is busy. This does not limit a cgroup's CPU usage if the CPUs are not busy. For further information, see Documentation/scheduler/sched-design-CFS.txt.
- In Linux 3.2, this controller was extended to provide CPU "bandwidth" control. If the kernel is configured with CONFIG_CFS_BANDWIDTH, then within each scheduling period (defined via a file in the cgroup directory), it is possible to define an upper limit on the CPU time allocated to the processes in a cgroup. This upper limit applies even if there is no other competition for the CPU. Further information can be found in the kernel source file Documentation/scheduler/sched-bwc.txt.
- cpuacct (since Linux 2.6.24; CONFIG_CGROUP_CPUACCT)
- This provides accounting for CPU usage by groups of processes.
- Further information can be found in the kernel source file Documentation/cgroup-v1/cpuacct.txt.
- cpuset (since Linux 2.6.24; CONFIG_CPUSETS)
- This cgroup can be used to bind the processes in a cgroup to a specified set of CPUs and NUMA nodes.
- Further information can be found in the kernel source file Documentation/cgroup-v1/cpusets.txt.
- memory (since Linux 2.6.25; CONFIG_MEMCG)
- The memory controller supports reporting and limiting of process memory, kernel memory, and swap used by cgroups.
- Further information can be found in the kernel source file Documentation/cgroup-v1/memory.txt.
- devices (since Linux 2.6.26; CONFIG_CGROUP_DEVICE)
- This supports controlling which processes may create (mknod) devices as well as open them for reading or writing. The policies may be specified as whitelists and blacklists. Hierarchy is enforced, so new rules must not violate existing rules for the target or ancestor cgroups.
- Further information can be found in the kernel source file Documentation/cgroup-v1/devices.txt.
- freezer (since Linux 2.6.28; CONFIG_CGROUP_FREEZER)
- The freezer cgroup can suspend and restore (resume) all processes in a cgroup. Freezing a cgroup /A also causes its children, for example, processes in /A/B, to be frozen.
- Further information can be found in the kernel source file Documentation/cgroup-v1/freezer-subsystem.txt.
- net_cls (since Linux 2.6.29; CONFIG_CGROUP_NET_CLASSID)
- This places a classid, specified for the cgroup, on network packets created by a cgroup. These classids can then be used in firewall rules, as well as used to shape traffic using tc(8). This applies only to packets leaving the cgroup, not to traffic arriving at the cgroup.
- Further information can be found in the kernel source file Documentation/cgroup-v1/net_cls.txt.
- blkio (since Linux 2.6.33; CONFIG_BLK_CGROUP)
- The blkio cgroup controls and limits access to specified block devices by applying IO control in the form of throttling and upper limits against leaf nodes and intermediate nodes in the storage hierarchy.
- Two policies are available. The first is a proportional-weight time-based division of disk implemented with CFQ. This is in effect for leaf nodes using CFQ. The second is a throttling policy which specifies upper I/O rate limits on a device.
- Further information can be found in the kernel source file Documentation/cgroup-v1/blkio-controller.txt.
- perf_event (since Linux 2.6.39; CONFIG_CGROUP_PERF)
- This controller allows perf monitoring of the set of processes grouped in a cgroup.
- Further information can be found in the kernel source file tools/perf/Documentation/perf-record.txt.
- net_prio (since Linux 3.3; CONFIG_CGROUP_NET_PRIO)
- This allows priorities to be specified, per network interface, for cgroups.
- Further information can be found in the kernel source file Documentation/cgroup-v1/net_prio.txt.
- hugetlb (since Linux 3.5; CONFIG_CGROUP_HUGETLB)
- This supports limiting the use of huge pages by cgroups.
- Further information can be found in the kernel source file Documentation/cgroup-v1/hugetlb.txt.
- pids (since Linux 4.3; CONFIG_CGROUP_PIDS)
- This controller permits limiting the number of process that may be created in a cgroup (and its descendants).
- Further information can be found in the kernel source file Documentation/cgroup-v1/pids.txt.
Creating cgroups and moving processesA cgroup filesystem initially contains a single root cgroup, '/', which all processes belong to. A new cgroup is created by creating a directory in the cgroup filesystem:
This creates a new empty cgroup.
A process may be moved to this cgroup by writing its PID into the cgroup's cgroup.procs file:
echo $$ > /sys/fs/cgroup/cpu/cg1/cgroup.procs
Only one PID at a time should be written to this file.
Writing the value 0 to a cgroup.procs file causes the writing process to be moved to the corresponding cgroup.
When writing a PID into the cgroup.procs, all threads in the process are moved into the new cgroup at once.
Within a hierarchy, a process can be a member of exactly one cgroup. Writing a process's PID to a cgroup.procs file automatically removes it from the cgroup of which it was previously a member.
The cgroup.procs file can be read to obtain a list of the processes that are members of a cgroup. The returned list of PIDs is not guaranteed to be in order. Nor is it guaranteed to be free of duplicates. (For example, a PID may be recycled while reading from the list.)
In cgroups v1 (but not cgroups v2), an individual thread can be moved to another cgroup by writing its thread ID (i.e., the kernel thread ID returned by clone(2) and gettid(2)) to the tasks file in a cgroup directory. This file can be read to discover the set of threads that are members of the cgroup. This file is not present in cgroup v2 directories.
Removing cgroupsTo remove a cgroup, it must first have no child cgroups and contain no (nonzombie) processes. So long as that is the case, one can simply remove the corresponding directory pathname. Note that files in a cgroup directory cannot and need not be removed.
Cgroups v1 release notificationTwo files can be used to determine whether the kernel provides notifications when a cgroup becomes empty. A cgroup is considered to be empty when it contains no child cgroups and no member processes.
A special file in the root directory of each cgroup hierarchy, release_agent, can be used to register the pathname of a program that may be invoked when a cgroup in the hierarchy becomes empty. The pathname of the newly empty cgroup (relative to the cgroup mount point) is provided as the sole command-line argument when the release_agent program is invoked. The release_agent program might remove the cgroup directory, or perhaps repopulate with a process.
The default value of the release_agent file is empty, meaning that no release agent is invoked.
Whether or not the release_agent program is invoked when a particular cgroup becomes empty is determined by the value in the notify_on_release file in the corresponding cgroup directory. If this file contains the value 0, then the release_agent program is not invoked. If it contains the value 1, the release_agent program is invoked. The default value for this file in the root cgroup is 0. At the time when a new cgroup is created, the value in this file is inherited from the corresponding file in the parent cgroup.
Cgroups version 2In cgroups v2, all mounted controllers reside in a single unified hierarchy. While (different) controllers may be simultaneously mounted under the v1 and v2 hierarchies, it is not possible to mount the same controller simultaneously under both the v1 and the v2 hierarchies.
The new behaviors in cgroups v2 are summarized here, and in some cases elaborated in the following subsections.
- Cgroups v2 provides a unified hierarchy against which all controllers are mounted.
- "Internal" processes are not permitted. With the exception of the root cgroup, processes may reside only in leaf nodes (cgroups that do not themselves contain child cgroups).
- Active cgroups must be specified via the files cgroup.controllers and cgroup.subtree_control.
- The tasks file has been removed. In addition, the cgroup.clone_children file that is employed by the cpuset controller has been removed.
- An improved mechanism for notification of empty cgroups is provided by the cgroup.events file.
For more changes, see the Documentation/cgroup-v2.txt file in the kernel source.
Cgroups v2 unified hierarchyIn cgroups v1, the ability to mount different controllers against different hierarchies was intended to allow great flexibility for application design. In practice, though, the flexibility turned out to less useful than expected, and in many cases added complexity. Therefore, in cgroups v2, all available controllers are mounted against a single hierarchy. The available controllers are automatically mounted, meaning that it is not necessary (or possible) to specify the controllers when mounting the cgroup v2 filesystem using a command such as the following:
mount -t cgroup2 none /mnt/cgroup2
A cgroup v2 controller is available only if it is not currently in use via a mount against a cgroup v1 hierarchy. Or, to put things another way, it is not possible to employ the same controller against both a v1 hierarchy and the unified v2 hierarchy.
Cgroups v2 no internal processes ruleWith the exception of the root cgroup, processes may reside only in leaf nodes (cgroups that do not themselves contain child cgroups). This avoids the need to decide how to partition resources between processes which are members of cgroup A and processes in child cgroups of A.
For instance, if cgroup /cg1/cg2 exists, then a process may reside in /cg1/cg2, but not in /cg1. This is to avoid an ambiguity in cgroups v1 with respect to the delegation of resources between processes in /cg1 and its child cgroups. The recommended approach in cgroups v2 is to create a subdirectory called leaf for any nonleaf cgroup which should contain processes, but no child cgroups. Thus, processes which previously would have gone into /cg1 would now go into /cg1/leaf. This has the advantage of making explicit the relationship between processes in /cg1/leaf and /cg1's other children.
Cgroups v2 subtree controlWhen a cgroup A/b is created, its cgroup.controllers file contains the list of controllers which were active in its parent, A. This is the list of controllers which are available to this cgroup. No controllers are active until they are enabled through the cgroup.subtree_control file, by writing the list of space-delimited names of the controllers, each preceded by '+' (to enable) or '-' (to disable). If the freezer controller is not enabled in /A/B, then it cannot be enabled in /A/B/C.
Cgroups v2 cgroup.events fileWith cgroups v2, a new mechanism is provided to obtain notification about when a cgroup becomes empty. The cgroups v1 release_agent and notify_on_release files are removed, and replaced by a new, more general-purpose file, cgroup.events. This file contains key-value pairs (delimited by newline characters, with the key and value separated by spaces) that identify events or state for a cgroup. Currently, only one key appears in this file, populated, which has either the value 0, meaning that the cgroup (and its descendants) contain no (nonzombie) processes, or 1, meaning that the cgroup contains member processes.
The cgroup.events file can be monitored, in order to receive notification when a cgroup transitions between the populated and unpopulated states (or vice versa). When monitoring this file using inotify(7), transitions generate IN_MODIFY events, and when monitoring the file using poll(2), transitions generate POLLPRI events.
The cgroups v2 notify_on_release mechanism offers at least two advantages over the cgroups v1 release_agent mechanism. First, it allows for cheaper notification, since a single process can monitor multiple cgroup.events files. By contrast, the cgroups v1 mechanism requires the creation of a process for each notification. Second, notification can be delegated to a process that lives inside a container associated with the newly empty cgroup.
- /proc/cgroups (since Linux 2.6.24)
- This file contains information about the controllers that are compiled into the kernel. An example of the contents of this file (reformatted for readability) is the following:
- #subsys_name hierarchy num_cgroups enabled cpuset 4 1 1 cpu 8 1 1 cpuacct 8 1 1 blkio 6 1 1 memory 3 1 1 devices 10 84 1 freezer 7 1 1 net_cls 9 1 1 perf_event 5 1 1 net_prio 9 1 1 hugetlb 0 1 0 pids 2 1 1
The fields in this file are, from left to right:
- The name of the controller.
The unique ID of the cgroup hierarchy on which this controller is mounted.
If multiple cgroups v1 controllers are bound to the same hierarchy,
then each will show the same hierarchy ID in this field.
The value in this field will be 0 if:
- the controller is not mounted on a cgroups v1 hierarchy;
- the controller is bound to the cgroups v2 single unified hierarchy; or
- the controller is disabled (see below).
- The number of control groups in this hierarchy using this controller.
- This field contains the value 1 if this controller is enabled, or 0 if it has been disabled (via the cgroup_disable kernel command-line boot parameter).
- /proc/[pid]/cgroup (since Linux 2.6.24)
- This file describes control groups to which the process with the corresponding PID belongs. The displayed information differs for cgroups version 1 and version 2 hierarchies.
- For each cgroup hierarchy of which the process is a member, there is one entry containing three colon-separated fields of the form:
- For example:
The colon-separated fields are, from left to right:
- For cgroups version 1 hierarchies, this field contains a unique hierarchy ID number that can be matched to a hierarchy ID in /proc/cgroups. For the cgroups version 2 hierarchy, this field contains the value 0.
- For cgroups version 1 hierarchies, this field contains a comma-separated list of the controllers bound to the hierarchy. For the cgroups version 2 hierarchy, this field is empty.
- This field contains the pathname of the control group in the hierarchy to which the process belongs. This pathname is relative to the mount point of the hierarchy.
ERRORSThe following errors can occur for mount(2):
- An attempt to mount a cgroup version 1 filesystem specified neither the name= option (to mount a named hierarchy) nor a controller name (or all).