1 ============= 2 CFS Scheduler 3 ============= 4 5 61. OVERVIEW 7 8CFS stands for "Completely Fair Scheduler," and is the new "desktop" process 9scheduler implemented by Ingo Molnar and merged in Linux 2.6.23. It is the 10replacement for the previous vanilla scheduler's SCHED_OTHER interactivity 11code. 12 1380% of CFS's design can be summed up in a single sentence: CFS basically models 14an "ideal, precise multi-tasking CPU" on real hardware. 15 16"Ideal multi-tasking CPU" is a (non-existent :-)) CPU that has 100% physical 17power and which can run each task at precise equal speed, in parallel, each at 181/nr_running speed. For example: if there are 2 tasks running, then it runs 19each at 50% physical power --- i.e., actually in parallel. 20 21On real hardware, we can run only a single task at once, so we have to 22introduce the concept of "virtual runtime." The virtual runtime of a task 23specifies when its next timeslice would start execution on the ideal 24multi-tasking CPU described above. In practice, the virtual runtime of a task 25is its actual runtime normalized to the total number of running tasks. 26 27 28 292. FEW IMPLEMENTATION DETAILS 30 31In CFS the virtual runtime is expressed and tracked via the per-task 32p->se.vruntime (nanosec-unit) value. This way, it's possible to accurately 33timestamp and measure the "expected CPU time" a task should have gotten. 34 35[ small detail: on "ideal" hardware, at any time all tasks would have the same 36 p->se.vruntime value --- i.e., tasks would execute simultaneously and no task 37 would ever get "out of balance" from the "ideal" share of CPU time. ] 38 39CFS's task picking logic is based on this p->se.vruntime value and it is thus 40very simple: it always tries to run the task with the smallest p->se.vruntime 41value (i.e., the task which executed least so far). CFS always tries to split 42up CPU time between runnable tasks as close to "ideal multitasking hardware" as 43possible. 44 45Most of the rest of CFS's design just falls out of this really simple concept, 46with a few add-on embellishments like nice levels, multiprocessing and various 47algorithm variants to recognize sleepers. 48 49 50 513. THE RBTREE 52 53CFS's design is quite radical: it does not use the old data structures for the 54runqueues, but it uses a time-ordered rbtree to build a "timeline" of future 55task execution, and thus has no "array switch" artifacts (by which both the 56previous vanilla scheduler and RSDL/SD are affected). 57 58CFS also maintains the rq->cfs.min_vruntime value, which is a monotonic 59increasing value tracking the smallest vruntime among all tasks in the 60runqueue. The total amount of work done by the system is tracked using 61min_vruntime; that value is used to place newly activated entities on the left 62side of the tree as much as possible. 63 64The total number of running tasks in the runqueue is accounted through the 65rq->cfs.load value, which is the sum of the weights of the tasks queued on the 66runqueue. 67 68CFS maintains a time-ordered rbtree, where all runnable tasks are sorted by the 69p->se.vruntime key. CFS picks the "leftmost" task from this tree and sticks to it. 70As the system progresses forwards, the executed tasks are put into the tree 71more and more to the right --- slowly but surely giving a chance for every task 72to become the "leftmost task" and thus get on the CPU within a deterministic 73amount of time. 74 75Summing up, CFS works like this: it runs a task a bit, and when the task 76schedules (or a scheduler tick happens) the task's CPU usage is "accounted 77for": the (small) time it just spent using the physical CPU is added to 78p->se.vruntime. Once p->se.vruntime gets high enough so that another task 79becomes the "leftmost task" of the time-ordered rbtree it maintains (plus a 80small amount of "granularity" distance relative to the leftmost task so that we 81do not over-schedule tasks and trash the cache), then the new leftmost task is 82picked and the current task is preempted. 83 84 85 864. SOME FEATURES OF CFS 87 88CFS uses nanosecond granularity accounting and does not rely on any jiffies or 89other HZ detail. Thus the CFS scheduler has no notion of "timeslices" in the 90way the previous scheduler had, and has no heuristics whatsoever. There is 91only one central tunable (you have to switch on CONFIG_SCHED_DEBUG): 92 93 /proc/sys/kernel/sched_min_granularity_ns 94 95which can be used to tune the scheduler from "desktop" (i.e., low latencies) to 96"server" (i.e., good batching) workloads. It defaults to a setting suitable 97for desktop workloads. SCHED_BATCH is handled by the CFS scheduler module too. 98 99Due to its design, the CFS scheduler is not prone to any of the "attacks" that 100exist today against the heuristics of the stock scheduler: fiftyp.c, thud.c, 101chew.c, ring-test.c, massive_intr.c all work fine and do not impact 102interactivity and produce the expected behavior. 103 104The CFS scheduler has a much stronger handling of nice levels and SCHED_BATCH 105than the previous vanilla scheduler: both types of workloads are isolated much 106more aggressively. 107 108SMP load-balancing has been reworked/sanitized: the runqueue-walking 109assumptions are gone from the load-balancing code now, and iterators of the 110scheduling modules are used. The balancing code got quite a bit simpler as a 111result. 112 113 114 1155. Scheduling policies 116 117CFS implements three scheduling policies: 118 119 - SCHED_NORMAL (traditionally called SCHED_OTHER): The scheduling 120 policy that is used for regular tasks. 121 122 - SCHED_BATCH: Does not preempt nearly as often as regular tasks 123 would, thereby allowing tasks to run longer and make better use of 124 caches but at the cost of interactivity. This is well suited for 125 batch jobs. 126 127 - SCHED_IDLE: This is even weaker than nice 19, but its not a true 128 idle timer scheduler in order to avoid to get into priority 129 inversion problems which would deadlock the machine. 130 131SCHED_FIFO/_RR are implemented in sched/rt.c and are as specified by 132POSIX. 133 134The command chrt from util-linux-ng 2.13.1.1 can set all of these except 135SCHED_IDLE. 136 137 138 1396. SCHEDULING CLASSES 140 141The new CFS scheduler has been designed in such a way to introduce "Scheduling 142Classes," an extensible hierarchy of scheduler modules. These modules 143encapsulate scheduling policy details and are handled by the scheduler core 144without the core code assuming too much about them. 145 146sched/fair.c implements the CFS scheduler described above. 147 148sched/rt.c implements SCHED_FIFO and SCHED_RR semantics, in a simpler way than 149the previous vanilla scheduler did. It uses 100 runqueues (for all 100 RT 150priority levels, instead of 140 in the previous scheduler) and it needs no 151expired array. 152 153Scheduling classes are implemented through the sched_class structure, which 154contains hooks to functions that must be called whenever an interesting event 155occurs. 156 157This is the (partial) list of the hooks: 158 159 - enqueue_task(...) 160 161 Called when a task enters a runnable state. 162 It puts the scheduling entity (task) into the red-black tree and 163 increments the nr_running variable. 164 165 - dequeue_task(...) 166 167 When a task is no longer runnable, this function is called to keep the 168 corresponding scheduling entity out of the red-black tree. It decrements 169 the nr_running variable. 170 171 - yield_task(...) 172 173 This function is basically just a dequeue followed by an enqueue, unless the 174 compat_yield sysctl is turned on; in that case, it places the scheduling 175 entity at the right-most end of the red-black tree. 176 177 - check_preempt_curr(...) 178 179 This function checks if a task that entered the runnable state should 180 preempt the currently running task. 181 182 - pick_next_task(...) 183 184 This function chooses the most appropriate task eligible to run next. 185 186 - set_curr_task(...) 187 188 This function is called when a task changes its scheduling class or changes 189 its task group. 190 191 - task_tick(...) 192 193 This function is mostly called from time tick functions; it might lead to 194 process switch. This drives the running preemption. 195 196 197 198 1997. GROUP SCHEDULER EXTENSIONS TO CFS 200 201Normally, the scheduler operates on individual tasks and strives to provide 202fair CPU time to each task. Sometimes, it may be desirable to group tasks and 203provide fair CPU time to each such task group. For example, it may be 204desirable to first provide fair CPU time to each user on the system and then to 205each task belonging to a user. 206 207CONFIG_CGROUP_SCHED strives to achieve exactly that. It lets tasks to be 208grouped and divides CPU time fairly among such groups. 209 210CONFIG_RT_GROUP_SCHED permits to group real-time (i.e., SCHED_FIFO and 211SCHED_RR) tasks. 212 213CONFIG_FAIR_GROUP_SCHED permits to group CFS (i.e., SCHED_NORMAL and 214SCHED_BATCH) tasks. 215 216 These options need CONFIG_CGROUPS to be defined, and let the administrator 217 create arbitrary groups of tasks, using the "cgroup" pseudo filesystem. See 218 Documentation/cgroups/cgroups.txt for more information about this filesystem. 219 220When CONFIG_FAIR_GROUP_SCHED is defined, a "cpu.shares" file is created for each 221group created using the pseudo filesystem. See example steps below to create 222task groups and modify their CPU share using the "cgroups" pseudo filesystem. 223 224 # mount -t tmpfs cgroup_root /sys/fs/cgroup 225 # mkdir /sys/fs/cgroup/cpu 226 # mount -t cgroup -ocpu none /sys/fs/cgroup/cpu 227 # cd /sys/fs/cgroup/cpu 228 229 # mkdir multimedia # create "multimedia" group of tasks 230 # mkdir browser # create "browser" group of tasks 231 232 # #Configure the multimedia group to receive twice the CPU bandwidth 233 # #that of browser group 234 235 # echo 2048 > multimedia/cpu.shares 236 # echo 1024 > browser/cpu.shares 237 238 # firefox & # Launch firefox and move it to "browser" group 239 # echo <firefox_pid> > browser/tasks 240 241 # #Launch gmplayer (or your favourite movie player) 242 # echo <movie_player_pid> > multimedia/tasks 243