1============= 2CFS Scheduler 3============= 4 5 61. OVERVIEW 7============ 8 9CFS stands for "Completely Fair Scheduler," and is the new "desktop" process 10scheduler implemented by Ingo Molnar and merged in Linux 2.6.23. It is the 11replacement for the previous vanilla scheduler's SCHED_OTHER interactivity 12code. 13 1480% of CFS's design can be summed up in a single sentence: CFS basically models 15an "ideal, precise multi-tasking CPU" on real hardware. 16 17"Ideal multi-tasking CPU" is a (non-existent :-)) CPU that has 100% physical 18power and which can run each task at precise equal speed, in parallel, each at 191/nr_running speed. For example: if there are 2 tasks running, then it runs 20each at 50% physical power --- i.e., actually in parallel. 21 22On real hardware, we can run only a single task at once, so we have to 23introduce the concept of "virtual runtime." The virtual runtime of a task 24specifies when its next timeslice would start execution on the ideal 25multi-tasking CPU described above. In practice, the virtual runtime of a task 26is its actual runtime normalized to the total number of running tasks. 27 28 29 302. FEW IMPLEMENTATION DETAILS 31============================== 32 33In CFS the virtual runtime is expressed and tracked via the per-task 34p->se.vruntime (nanosec-unit) value. This way, it's possible to accurately 35timestamp and measure the "expected CPU time" a task should have gotten. 36 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. 40 41CFS's task picking logic is based on this p->se.vruntime value and it is thus 42very simple: it always tries to run the task with the smallest p->se.vruntime 43value (i.e., the task which executed least so far). CFS always tries to split 44up CPU time between runnable tasks as close to "ideal multitasking hardware" as 45possible. 46 47Most of the rest of CFS's design just falls out of this really simple concept, 48with a few add-on embellishments like nice levels, multiprocessing and various 49algorithm variants to recognize sleepers. 50 51 52 533. THE RBTREE 54============== 55 56CFS's design is quite radical: it does not use the old data structures for the 57runqueues, but it uses a time-ordered rbtree to build a "timeline" of future 58task execution, and thus has no "array switch" artifacts (by which both the 59previous vanilla scheduler and RSDL/SD are affected). 60 61CFS also maintains the rq->cfs.min_vruntime value, which is a monotonic 62increasing value tracking the smallest vruntime among all tasks in the 63runqueue. The total amount of work done by the system is tracked using 64min_vruntime; that value is used to place newly activated entities on the left 65side of the tree as much as possible. 66 67The total number of running tasks in the runqueue is accounted through the 68rq->cfs.load value, which is the sum of the weights of the tasks queued on the 69runqueue. 70 71CFS maintains a time-ordered rbtree, where all runnable tasks are sorted by the 72p->se.vruntime key. CFS picks the "leftmost" task from this tree and sticks to it. 73As the system progresses forwards, the executed tasks are put into the tree 74more and more to the right --- slowly but surely giving a chance for every task 75to become the "leftmost task" and thus get on the CPU within a deterministic 76amount of time. 77 78Summing up, CFS works like this: it runs a task a bit, and when the task 79schedules (or a scheduler tick happens) the task's CPU usage is "accounted 80for": the (small) time it just spent using the physical CPU is added to 81p->se.vruntime. Once p->se.vruntime gets high enough so that another task 82becomes the "leftmost task" of the time-ordered rbtree it maintains (plus a 83small amount of "granularity" distance relative to the leftmost task so that we 84do not over-schedule tasks and trash the cache), then the new leftmost task is 85picked and the current task is preempted. 86 87 88 894. SOME FEATURES OF CFS 90======================== 91 92CFS uses nanosecond granularity accounting and does not rely on any jiffies or 93other HZ detail. Thus the CFS scheduler has no notion of "timeslices" in the 94way the previous scheduler had, and has no heuristics whatsoever. There is 95only one central tunable (you have to switch on CONFIG_SCHED_DEBUG): 96 97 /sys/kernel/debug/sched/base_slice_ns 98 99which 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 101for desktop workloads. SCHED_BATCH is handled by the CFS scheduler module too. 102 103Due to its design, the CFS scheduler is not prone to any of the "attacks" that 104exist today against the heuristics of the stock scheduler: fiftyp.c, thud.c, 105chew.c, ring-test.c, massive_intr.c all work fine and do not impact 106interactivity and produce the expected behavior. 107 108The CFS scheduler has a much stronger handling of nice levels and SCHED_BATCH 109than the previous vanilla scheduler: both types of workloads are isolated much 110more aggressively. 111 112SMP load-balancing has been reworked/sanitized: the runqueue-walking 113assumptions are gone from the load-balancing code now, and iterators of the 114scheduling modules are used. The balancing code got quite a bit simpler as a 115result. 116 117 118 1195. Scheduling policies 120====================== 121 122CFS implements three scheduling policies: 123 124 - SCHED_NORMAL (traditionally called SCHED_OTHER): The scheduling 125 policy that is used for regular tasks. 126 127 - 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 130 batch jobs. 131 132 - 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. 135 136SCHED_FIFO/_RR are implemented in sched/rt.c and are as specified by 137POSIX. 138 139The command chrt from util-linux-ng 2.13.1.1 can set all of these except 140SCHED_IDLE. 141 142 143 1446. SCHEDULING CLASSES 145====================== 146 147The new CFS scheduler has been designed in such a way to introduce "Scheduling 148Classes," an extensible hierarchy of scheduler modules. These modules 149encapsulate scheduling policy details and are handled by the scheduler core 150without the core code assuming too much about them. 151 152sched/fair.c implements the CFS scheduler described above. 153 154sched/rt.c implements SCHED_FIFO and SCHED_RR semantics, in a simpler way than 155the previous vanilla scheduler did. It uses 100 runqueues (for all 100 RT 156priority levels, instead of 140 in the previous scheduler) and it needs no 157expired array. 158 159Scheduling classes are implemented through the sched_class structure, which 160contains hooks to functions that must be called whenever an interesting event 161occurs. 162 163This is the (partial) list of the hooks: 164 165 - enqueue_task(...) 166 167 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. 170 171 - dequeue_task(...) 172 173 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. 176 177 - yield_task(...) 178 179 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. 182 183 - wakeup_preempt(...) 184 185 This function checks if a task that entered the runnable state should 186 preempt the currently running task. 187 188 - pick_next_task(...) 189 190 This function chooses the most appropriate task eligible to run next. 191 192 - set_next_task(...) 193 194 This function is called when a task changes its scheduling class, changes 195 its task group or is scheduled. 196 197 - task_tick(...) 198 199 This function is mostly called from time tick functions; it might lead to 200 process switch. This drives the running preemption. 201 202 203 204 2057. GROUP SCHEDULER EXTENSIONS TO CFS 206===================================== 207 208Normally, the scheduler operates on individual tasks and strives to provide 209fair CPU time to each task. Sometimes, it may be desirable to group tasks and 210provide fair CPU time to each such task group. For example, it may be 211desirable to first provide fair CPU time to each user on the system and then to 212each task belonging to a user. 213 214CONFIG_CGROUP_SCHED strives to achieve exactly that. It lets tasks to be 215grouped and divides CPU time fairly among such groups. 216 217CONFIG_RT_GROUP_SCHED permits to group real-time (i.e., SCHED_FIFO and 218SCHED_RR) tasks. 219 220CONFIG_FAIR_GROUP_SCHED permits to group CFS (i.e., SCHED_NORMAL and 221SCHED_BATCH) tasks. 222 223 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. 226 227When CONFIG_FAIR_GROUP_SCHED is defined, a "cpu.shares" file is created for each 228group created using the pseudo filesystem. See example steps below to create 229task groups and modify their CPU share using the "cgroups" pseudo filesystem:: 230 231 # 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 235 236 # mkdir multimedia # create "multimedia" group of tasks 237 # mkdir browser # create "browser" group of tasks 238 239 # #Configure the multimedia group to receive twice the CPU bandwidth 240 # #that of browser group 241 242 # echo 2048 > multimedia/cpu.shares 243 # echo 1024 > browser/cpu.shares 244 245 # firefox & # Launch firefox and move it to "browser" group 246 # echo <firefox_pid> > browser/tasks 247 248 # #Launch gmplayer (or your favourite movie player) 249 # echo <movie_player_pid> > multimedia/tasks 250