void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
{
- s64 left_vruntime = -1, min_vruntime, right_vruntime = -1, left_deadline = -1, spread;
+ s64 left_vruntime = -1, zero_vruntime, right_vruntime = -1, left_deadline = -1, spread;
struct sched_entity *last, *first, *root;
struct rq *rq = cpu_rq(cpu);
unsigned long flags;
last = __pick_last_entity(cfs_rq);
if (last)
right_vruntime = last->vruntime;
- min_vruntime = cfs_rq->min_vruntime;
+ zero_vruntime = cfs_rq->zero_vruntime;
raw_spin_rq_unlock_irqrestore(rq, flags);
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "left_deadline",
SPLIT_NS(left_deadline));
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "left_vruntime",
SPLIT_NS(left_vruntime));
- SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "min_vruntime",
- SPLIT_NS(min_vruntime));
+ SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "zero_vruntime",
+ SPLIT_NS(zero_vruntime));
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "avg_vruntime",
SPLIT_NS(avg_vruntime(cfs_rq)));
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "right_vruntime",
static inline s64 entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
- return (s64)(se->vruntime - cfs_rq->min_vruntime);
+ return (s64)(se->vruntime - cfs_rq->zero_vruntime);
}
#define __node_2_se(node) \
*
* Which we track using:
*
- * v0 := cfs_rq->min_vruntime
+ * v0 := cfs_rq->zero_vruntime
* \Sum (v_i - v0) * w_i := cfs_rq->avg_vruntime
* \Sum w_i := cfs_rq->avg_load
*
- * Since min_vruntime is a monotonic increasing variable that closely tracks
- * the per-task service, these deltas: (v_i - v), will be in the order of the
- * maximal (virtual) lag induced in the system due to quantisation.
+ * Since zero_vruntime closely tracks the per-task service, these
+ * deltas: (v_i - v), will be in the order of the maximal (virtual) lag
+ * induced in the system due to quantisation.
*
* Also, we use scale_load_down() to reduce the size.
*
avg = div_s64(avg, load);
}
- return cfs_rq->min_vruntime + avg;
+ return cfs_rq->zero_vruntime + avg;
}
/*
load += weight;
}
- return avg >= (s64)(vruntime - cfs_rq->min_vruntime) * load;
+ return avg >= (s64)(vruntime - cfs_rq->zero_vruntime) * load;
}
int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se)
return vruntime_eligible(cfs_rq, se->vruntime);
}
-static u64 __update_min_vruntime(struct cfs_rq *cfs_rq, u64 vruntime)
+static void update_zero_vruntime(struct cfs_rq *cfs_rq)
{
- u64 min_vruntime = cfs_rq->min_vruntime;
- /*
- * open coded max_vruntime() to allow updating avg_vruntime
- */
- s64 delta = (s64)(vruntime - min_vruntime);
- if (delta > 0) {
- avg_vruntime_update(cfs_rq, delta);
- min_vruntime = vruntime;
- }
- return min_vruntime;
-}
+ u64 vruntime = avg_vruntime(cfs_rq);
+ s64 delta = (s64)(vruntime - cfs_rq->zero_vruntime);
-static void update_min_vruntime(struct cfs_rq *cfs_rq)
-{
- struct sched_entity *se = __pick_root_entity(cfs_rq);
- struct sched_entity *curr = cfs_rq->curr;
- u64 vruntime = cfs_rq->min_vruntime;
-
- if (curr) {
- if (curr->on_rq)
- vruntime = curr->vruntime;
- else
- curr = NULL;
- }
+ avg_vruntime_update(cfs_rq, delta);
- if (se) {
- if (!curr)
- vruntime = se->min_vruntime;
- else
- vruntime = min_vruntime(vruntime, se->min_vruntime);
- }
-
- /* ensure we never gain time by being placed backwards. */
- cfs_rq->min_vruntime = __update_min_vruntime(cfs_rq, vruntime);
+ cfs_rq->zero_vruntime = vruntime;
}
static inline u64 cfs_rq_min_slice(struct cfs_rq *cfs_rq)
static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
avg_vruntime_add(cfs_rq, se);
+ update_zero_vruntime(cfs_rq);
se->min_vruntime = se->vruntime;
se->min_slice = se->slice;
rb_add_augmented_cached(&se->run_node, &cfs_rq->tasks_timeline,
rb_erase_augmented_cached(&se->run_node, &cfs_rq->tasks_timeline,
&min_vruntime_cb);
avg_vruntime_sub(cfs_rq, se);
+ update_zero_vruntime(cfs_rq);
}
struct sched_entity *__pick_root_entity(struct cfs_rq *cfs_rq)
curr->vruntime += calc_delta_fair(delta_exec, curr);
resched = update_deadline(cfs_rq, curr);
- update_min_vruntime(cfs_rq);
if (entity_is_task(curr)) {
/*
if (!curr)
__enqueue_entity(cfs_rq, se);
cfs_rq->nr_queued++;
-
- /*
- * The entity's vruntime has been adjusted, so let's check
- * whether the rq-wide min_vruntime needs updated too. Since
- * the calculations above require stable min_vruntime rather
- * than up-to-date one, we do the update at the end of the
- * reweight process.
- */
- update_min_vruntime(cfs_rq);
}
}
update_cfs_group(se);
- /*
- * Now advance min_vruntime if @se was the entity holding it back,
- * except when: DEQUEUE_SAVE && !DEQUEUE_MOVE, in this case we'll be
- * put back on, and if we advance min_vruntime, we'll be placed back
- * further than we started -- i.e. we'll be penalized.
- */
- if ((flags & (DEQUEUE_SAVE | DEQUEUE_MOVE)) != DEQUEUE_SAVE)
- update_min_vruntime(cfs_rq);
-
if (flags & DEQUEUE_DELAYED)
finish_delayed_dequeue_entity(se);
if (entity_eligible(cfs_rq, se)) {
se->vruntime = se->deadline;
se->deadline += calc_delta_fair(se->slice, se);
- update_min_vruntime(cfs_rq);
}
}
* Which shows that S and s_i transform alike (which makes perfect sense
* given that S is basically the (weighted) average of s_i).
*
- * Then:
- *
- * x -> s_min := min{s_i} (8)
- *
- * to obtain:
- *
- * \Sum_i w_i (s_i - s_min)
- * S = s_min + ------------------------ (9)
- * \Sum_i w_i
- *
- * Which already looks familiar, and is the basis for our current
- * approximation:
- *
- * S ~= s_min (10)
- *
- * Now, obviously, (10) is absolute crap :-), but it sorta works.
- *
* So the thing to remember is that the above is strictly UP. It is
* possible to generalize to multiple runqueues -- however it gets really
* yuck when you have to add affinity support, as illustrated by our very
* Let, for our runqueue 'k':
*
* T_k = \Sum_i w_i s_i
- * W_k = \Sum_i w_i ; for all i of k (11)
+ * W_k = \Sum_i w_i ; for all i of k (8)
*
* Then we can write (6) like:
*
* T_k
- * S_k = --- (12)
+ * S_k = --- (9)
* W_k
*
* From which immediately follows that:
*
* T_k + T_l
- * S_k+l = --------- (13)
+ * S_k+l = --------- (10)
* W_k + W_l
*
* On which we can define a combined lag:
*
- * lag_k+l(i) := S_k+l - s_i (14)
+ * lag_k+l(i) := S_k+l - s_i (11)
*
* And that gives us the tools to compare tasks across a combined runqueue.
*
* using (7); this only requires storing single 'time'-stamps.
*
* b) when comparing tasks between 2 runqueues of which one is forced-idle,
- * compare the combined lag, per (14).
+ * compare the combined lag, per (11).
*
* Now, of course cgroups (I so hate them) make this more interesting in
* that a) seems to suggest we need to iterate all cgroup on a CPU at such
* every tick. This limits the observed divergence due to the work
* conservancy.
*
- * On top of that, we can improve upon things by moving away from our
- * horrible (10) hack and moving to (9) and employing (13) here.
+ * On top of that, we can improve upon things by employing (10) here.
*/
/*
- * se_fi_update - Update the cfs_rq->min_vruntime_fi in a CFS hierarchy if needed.
+ * se_fi_update - Update the cfs_rq->zero_vruntime_fi in a CFS hierarchy if needed.
*/
static void se_fi_update(const struct sched_entity *se, unsigned int fi_seq,
bool forceidle)
cfs_rq->forceidle_seq = fi_seq;
}
- cfs_rq->min_vruntime_fi = cfs_rq->min_vruntime;
+ cfs_rq->zero_vruntime_fi = cfs_rq->zero_vruntime;
}
}
/*
* Find delta after normalizing se's vruntime with its cfs_rq's
- * min_vruntime_fi, which would have been updated in prior calls
+ * zero_vruntime_fi, which would have been updated in prior calls
* to se_fi_update().
*/
delta = (s64)(sea->vruntime - seb->vruntime) +
- (s64)(cfs_rqb->min_vruntime_fi - cfs_rqa->min_vruntime_fi);
+ (s64)(cfs_rqb->zero_vruntime_fi - cfs_rqa->zero_vruntime_fi);
return delta > 0;
}
void init_cfs_rq(struct cfs_rq *cfs_rq)
{
cfs_rq->tasks_timeline = RB_ROOT_CACHED;
- cfs_rq->min_vruntime = (u64)(-(1LL << 20));
+ cfs_rq->zero_vruntime = (u64)(-(1LL << 20));
raw_spin_lock_init(&cfs_rq->removed.lock);
}