diff options
| author | Peter Zijlstra <peterz@infradead.org> | 2023-11-04 11:59:21 +0100 |
|---|---|---|
| committer | Peter Zijlstra <peterz@infradead.org> | 2023-11-15 09:57:51 +0100 |
| commit | 63ba8422f876e32ee564ea95da9a7313b13ff0a1 (patch) | |
| tree | d121359e9386adb64a5538b43ead02166d78cb7b /kernel/sched/core.c | |
| parent | 2f7a0f58948d8231236e2facecc500f1930fb996 (diff) | |
sched/deadline: Introduce deadline servers
Low priority tasks (e.g., SCHED_OTHER) can suffer starvation if tasks
with higher priority (e.g., SCHED_FIFO) monopolize CPU(s).
RT Throttling has been introduced a while ago as a (mostly debug)
countermeasure one can utilize to reserve some CPU time for low priority
tasks (usually background type of work, e.g. workqueues, timers, etc.).
It however has its own problems (see documentation) and the undesired
effect of unconditionally throttling FIFO tasks even when no lower
priority activity needs to run (there are mechanisms to fix this issue
as well, but, again, with their own problems).
Introduce deadline servers to service low priority tasks needs under
starvation conditions. Deadline servers are built extending SCHED_DEADLINE
implementation to allow 2-level scheduling (a sched_deadline entity
becomes a container for lower priority scheduling entities).
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Daniel Bristot de Oliveira <bristot@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/4968601859d920335cf85822eb573a5f179f04b8.1699095159.git.bristot@kernel.org
Diffstat (limited to 'kernel/sched/core.c')
| -rw-r--r-- | kernel/sched/core.c | 17 |
1 files changed, 17 insertions, 0 deletions
diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 966631f05d71..f5f4495d1768 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3797,6 +3797,8 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags, rq->idle_stamp = 0; } #endif + + p->dl_server = NULL; } /* @@ -6003,12 +6005,27 @@ __pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) p = pick_next_task_idle(rq); } + /* + * This is the fast path; it cannot be a DL server pick; + * therefore even if @p == @prev, ->dl_server must be NULL. + */ + if (p->dl_server) + p->dl_server = NULL; + return p; } restart: put_prev_task_balance(rq, prev, rf); + /* + * We've updated @prev and no longer need the server link, clear it. + * Must be done before ->pick_next_task() because that can (re)set + * ->dl_server. + */ + if (prev->dl_server) + prev->dl_server = NULL; + for_each_class(class) { p = class->pick_next_task(rq); if (p) |