Documentation/scheduler/sched-deadline.rst

11       2.2 Bandwidth reclaiming
17     4. Bandwidth management
42  algorithm, augmented with a mechanism (called Constant Bandwidth Server, CBS)
62  "admission control" strategy (see Section "4. Bandwidth management") is used
67  interference between different tasks (bandwidth isolation), while the EDF[1]
125 2.2 Bandwidth reclaiming
128  Bandwidth reclaiming for deadline tasks is based on the GRUB (Greedy
129  Reclamation of Unused Bandwidth) algorithm [15, 16, 17] and it is enabled
164       bandwidth cannot be immediately reclaimed without breaking the
167       the 0-lag time, when the task's bandwidth can be reclaimed without
200   - Active bandwidth (running_bw): this is the sum of the bandwidths of all
203   - Total bandwidth (this_bw): this is the sum of all tasks "belonging" to the
206   - Maximum usable bandwidth (max_bw): This is the maximum bandwidth usable by
210  The algorithm reclaims the bandwidth of the tasks in Inactive state.
218   - Ui is the bandwidth of task Ti;
228  to 4 and period equal to 8 (i.e., bandwidth equal to 0.5)::
277     meantime, it enters the Inactive state. Its bandwidth is removed from
281     Task T2 therefore reclaims the bandwidth unused by Task T1.
534   15 - G. Lipari, S. Baruah, Greedy reclamation of unused bandwidth in
535        constant-bandwidth servers, 12th IEEE Euromicro Conference on Real-Time
551 4. Bandwidth management
567  "bandwidth".
568  The interface used to control the CPU bandwidth that can be allocated
575  figure out how we want to manage SCHED_DEADLINE bandwidth at the task group
578  A main difference between deadline bandwidth management and RT-throttling
579  is that -deadline tasks have bandwidth on their own (while -rt ones don't!),
581  desired bandwidth. In other words, this means that interface parameters are
584  parameters, so that CPU bandwidth is allocated to SCHED_DEADLINE tasks
598  run -rt tasks from a -deadline server; in which case the -rt bandwidth is a
606  It is also possible to disable this bandwidth management logic, and
638  The default value for SCHED_DEADLINE bandwidth is to have rt_runtime equal to
646  Section 5), then this simple setting of the bandwidth management is able to
665  future with bandwidth reclaiming mechanisms, where sched_yield() will
704     of retaining bandwidth isolation among non-interacting tasks. This is
707   - (c)group based bandwidth management, and maybe scheduling;