9 CFS stands for "Completely Fair Scheduler," and is the new "desktop" process
10 scheduler implemented by Ingo Molnar and merged in Linux 2.6.23. It is the
11 replacement for the previous vanilla scheduler's SCHED_OTHER interactivity
14 80% of CFS's design can be summed up in a single sentence: CFS basically models
15 an "ideal, precise multi-tasking CPU" on real hardware.
17 "Ideal multi-tasking CPU" is a (non-existent :-)) CPU that has 100% physical
18 power and which can run each task at precise equal speed, in parallel, each at
19 1/nr_running speed. For example: if there are 2 tasks running, then it runs
20 each at 50% physical power --- i.e., actually in parallel.
22 On real hardware, we can run only a single task at once, so we have to
23 introduce the concept of "virtual runtime." The virtual runtime of a task
24 specifies when its next timeslice would start execution on the ideal
25 multi-tasking CPU described above. In practice, the virtual runtime of a task
26 is its actual runtime normalized to the total number of running tasks.
30 2. FEW IMPLEMENTATION DETAILS
31 ==============================
33 In CFS the virtual runtime is expressed and tracked via the per-task
34 p->se.vruntime (nanosec-unit) value. This way, it's possible to accurately
35 timestamp and measure the "expected CPU time" a task should have gotten.
37 Small detail: on "ideal" hardware, at any time all tasks would have the same
38 p->se.vruntime value --- i.e., tasks would execute simultaneously and no task
39 would ever get "out of balance" from the "ideal" share of CPU time.
41 CFS's task picking logic is based on this p->se.vruntime value and it is thus
42 very simple: it always tries to run the task with the smallest p->se.vruntime
43 value (i.e., the task which executed least so far). CFS always tries to split
44 up CPU time between runnable tasks as close to "ideal multitasking hardware" as
47 Most of the rest of CFS's design just falls out of this really simple concept,
48 with a few add-on embellishments like nice levels, multiprocessing and various
49 algorithm variants to recognize sleepers.
56 CFS's design is quite radical: it does not use the old data structures for the
57 runqueues, but it uses a time-ordered rbtree to build a "timeline" of future
58 task execution, and thus has no "array switch" artifacts (by which both the
59 previous vanilla scheduler and RSDL/SD are affected).
61 CFS also maintains the rq->cfs.min_vruntime value, which is a monotonic
62 increasing value tracking the smallest vruntime among all tasks in the
63 runqueue. The total amount of work done by the system is tracked using
64 min_vruntime; that value is used to place newly activated entities on the left
65 side of the tree as much as possible.
67 The total number of running tasks in the runqueue is accounted through the
68 rq->cfs.load value, which is the sum of the weights of the tasks queued on the
71 CFS maintains a time-ordered rbtree, where all runnable tasks are sorted by the
72 p->se.vruntime key. CFS picks the "leftmost" task from this tree and sticks to it.
73 As the system progresses forwards, the executed tasks are put into the tree
74 more and more to the right --- slowly but surely giving a chance for every task
75 to become the "leftmost task" and thus get on the CPU within a deterministic
78 Summing up, CFS works like this: it runs a task a bit, and when the task
79 schedules (or a scheduler tick happens) the task's CPU usage is "accounted
80 for": the (small) time it just spent using the physical CPU is added to
81 p->se.vruntime. Once p->se.vruntime gets high enough so that another task
82 becomes the "leftmost task" of the time-ordered rbtree it maintains (plus a
83 small amount of "granularity" distance relative to the leftmost task so that we
84 do not over-schedule tasks and trash the cache), then the new leftmost task is
85 picked and the current task is preempted.
89 4. SOME FEATURES OF CFS
90 ========================
92 CFS uses nanosecond granularity accounting and does not rely on any jiffies or
93 other HZ detail. Thus the CFS scheduler has no notion of "timeslices" in the
94 way the previous scheduler had, and has no heuristics whatsoever. There is
95 only one central tunable (you have to switch on CONFIG_SCHED_DEBUG):
97 /sys/kernel/debug/sched/min_granularity_ns
99 which can be used to tune the scheduler from "desktop" (i.e., low latencies) to
100 "server" (i.e., good batching) workloads. It defaults to a setting suitable
101 for desktop workloads. SCHED_BATCH is handled by the CFS scheduler module too.
103 Due to its design, the CFS scheduler is not prone to any of the "attacks" that
104 exist today against the heuristics of the stock scheduler: fiftyp.c, thud.c,
105 chew.c, ring-test.c, massive_intr.c all work fine and do not impact
106 interactivity and produce the expected behavior.
108 The CFS scheduler has a much stronger handling of nice levels and SCHED_BATCH
109 than the previous vanilla scheduler: both types of workloads are isolated much
112 SMP load-balancing has been reworked/sanitized: the runqueue-walking
113 assumptions are gone from the load-balancing code now, and iterators of the
114 scheduling modules are used. The balancing code got quite a bit simpler as a
119 5. Scheduling policies
120 ======================
122 CFS implements three scheduling policies:
124 - SCHED_NORMAL (traditionally called SCHED_OTHER): The scheduling
125 policy that is used for regular tasks.
127 - SCHED_BATCH: Does not preempt nearly as often as regular tasks
128 would, thereby allowing tasks to run longer and make better use of
129 caches but at the cost of interactivity. This is well suited for
132 - SCHED_IDLE: This is even weaker than nice 19, but its not a true
133 idle timer scheduler in order to avoid to get into priority
134 inversion problems which would deadlock the machine.
136 SCHED_FIFO/_RR are implemented in sched/rt.c and are as specified by
139 The command chrt from util-linux-ng 2.13.1.1 can set all of these except
144 6. SCHEDULING CLASSES
145 ======================
147 The new CFS scheduler has been designed in such a way to introduce "Scheduling
148 Classes," an extensible hierarchy of scheduler modules. These modules
149 encapsulate scheduling policy details and are handled by the scheduler core
150 without the core code assuming too much about them.
152 sched/fair.c implements the CFS scheduler described above.
154 sched/rt.c implements SCHED_FIFO and SCHED_RR semantics, in a simpler way than
155 the previous vanilla scheduler did. It uses 100 runqueues (for all 100 RT
156 priority levels, instead of 140 in the previous scheduler) and it needs no
159 Scheduling classes are implemented through the sched_class structure, which
160 contains hooks to functions that must be called whenever an interesting event
163 This is the (partial) list of the hooks:
167 Called when a task enters a runnable state.
168 It puts the scheduling entity (task) into the red-black tree and
169 increments the nr_running variable.
173 When a task is no longer runnable, this function is called to keep the
174 corresponding scheduling entity out of the red-black tree. It decrements
175 the nr_running variable.
179 This function is basically just a dequeue followed by an enqueue, unless the
180 compat_yield sysctl is turned on; in that case, it places the scheduling
181 entity at the right-most end of the red-black tree.
183 - check_preempt_curr(...)
185 This function checks if a task that entered the runnable state should
186 preempt the currently running task.
188 - pick_next_task(...)
190 This function chooses the most appropriate task eligible to run next.
194 This function is called when a task changes its scheduling class or changes
199 This function is mostly called from time tick functions; it might lead to
200 process switch. This drives the running preemption.
205 7. GROUP SCHEDULER EXTENSIONS TO CFS
206 =====================================
208 Normally, the scheduler operates on individual tasks and strives to provide
209 fair CPU time to each task. Sometimes, it may be desirable to group tasks and
210 provide fair CPU time to each such task group. For example, it may be
211 desirable to first provide fair CPU time to each user on the system and then to
212 each task belonging to a user.
214 CONFIG_CGROUP_SCHED strives to achieve exactly that. It lets tasks to be
215 grouped and divides CPU time fairly among such groups.
217 CONFIG_RT_GROUP_SCHED permits to group real-time (i.e., SCHED_FIFO and
220 CONFIG_FAIR_GROUP_SCHED permits to group CFS (i.e., SCHED_NORMAL and
223 These options need CONFIG_CGROUPS to be defined, and let the administrator
224 create arbitrary groups of tasks, using the "cgroup" pseudo filesystem. See
225 Documentation/admin-guide/cgroup-v1/cgroups.rst for more information about this filesystem.
227 When CONFIG_FAIR_GROUP_SCHED is defined, a "cpu.shares" file is created for each
228 group created using the pseudo filesystem. See example steps below to create
229 task groups and modify their CPU share using the "cgroups" pseudo filesystem::
231 # mount -t tmpfs cgroup_root /sys/fs/cgroup
232 # mkdir /sys/fs/cgroup/cpu
233 # mount -t cgroup -ocpu none /sys/fs/cgroup/cpu
234 # cd /sys/fs/cgroup/cpu
236 # mkdir multimedia # create "multimedia" group of tasks
237 # mkdir browser # create "browser" group of tasks
239 # #Configure the multimedia group to receive twice the CPU bandwidth
240 # #that of browser group
242 # echo 2048 > multimedia/cpu.shares
243 # echo 1024 > browser/cpu.shares
245 # firefox & # Launch firefox and move it to "browser" group
246 # echo <firefox_pid> > browser/tasks
248 # #Launch gmplayer (or your favourite movie player)
249 # echo <movie_player_pid> > multimedia/tasks