unsigned long flags;
struct bfq_io_cq *icq;
- spin_lock_irqsave(q->queue_lock, flags);
+ spin_lock_irqsave(&q->queue_lock, flags);
icq = icq_to_bic(ioc_lookup_icq(ioc, q));
- spin_unlock_irqrestore(q->queue_lock, flags);
+ spin_unlock_irqrestore(&q->queue_lock, flags);
return icq;
}
bfqq->pos_root = NULL;
}
-/*
- * Tell whether there are active queues with different weights or
- * active groups.
- */
-static bool bfq_varied_queue_weights_or_active_groups(struct bfq_data *bfqd)
-{
- /*
- * For queue weights to differ, queue_weights_tree must contain
- * at least two nodes.
- */
- return (!RB_EMPTY_ROOT(&bfqd->queue_weights_tree) &&
- (bfqd->queue_weights_tree.rb_node->rb_left ||
- bfqd->queue_weights_tree.rb_node->rb_right)
-#ifdef CONFIG_BFQ_GROUP_IOSCHED
- ) ||
- (bfqd->num_groups_with_pending_reqs > 0
-#endif
- );
-}
-
/*
* The following function returns true if every queue must receive the
* same share of the throughput (this condition is used when deciding
*
* Such a scenario occurs when:
* 1) all active queues have the same weight,
- * 2) all active groups at the same level in the groups tree have the same
- * weight,
+ * 2) all active queues belong to the same I/O-priority class,
* 3) all active groups at the same level in the groups tree have the same
+ * weight,
+ * 4) all active groups at the same level in the groups tree have the same
* number of children.
*
* Unfortunately, keeping the necessary state for evaluating exactly
* the last two symmetry sub-conditions above would be quite complex
- * and time consuming. Therefore this function evaluates, instead,
- * only the following stronger two sub-conditions, for which it is
+ * and time consuming. Therefore this function evaluates, instead,
+ * only the following stronger three sub-conditions, for which it is
* much easier to maintain the needed state:
* 1) all active queues have the same weight,
- * 2) there are no active groups.
+ * 2) all active queues belong to the same I/O-priority class,
+ * 3) there are no active groups.
* In particular, the last condition is always true if hierarchical
* support or the cgroups interface are not enabled, thus no state
* needs to be maintained in this case.
*/
static bool bfq_symmetric_scenario(struct bfq_data *bfqd)
{
- return !bfq_varied_queue_weights_or_active_groups(bfqd);
+ /*
+ * For queue weights to differ, queue_weights_tree must contain
+ * at least two nodes.
+ */
+ bool varied_queue_weights = !RB_EMPTY_ROOT(&bfqd->queue_weights_tree) &&
+ (bfqd->queue_weights_tree.rb_node->rb_left ||
+ bfqd->queue_weights_tree.rb_node->rb_right);
+
+ bool multiple_classes_busy =
+ (bfqd->busy_queues[0] && bfqd->busy_queues[1]) ||
+ (bfqd->busy_queues[0] && bfqd->busy_queues[2]) ||
+ (bfqd->busy_queues[1] && bfqd->busy_queues[2]);
+
+ /*
+ * For queue weights to differ, queue_weights_tree must contain
+ * at least two nodes.
+ */
+ return !(varied_queue_weights || multiple_classes_busy
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
+ || bfqd->num_groups_with_pending_reqs > 0
+#endif
+ );
}
/*
/*
* In the unlucky event of an allocation failure, we just
* exit. This will cause the weight of queue to not be
- * considered in bfq_varied_queue_weights_or_active_groups,
- * which, in its turn, causes the scenario to be deemed
- * wrongly symmetric in case bfqq's weight would have been
- * the only weight making the scenario asymmetric. On the
- * bright side, no unbalance will however occur when bfqq
- * becomes inactive again (the invocation of this function
- * is triggered by an activation of queue). In fact,
- * bfq_weights_tree_remove does nothing if
- * !bfqq->weight_counter.
+ * considered in bfq_symmetric_scenario, which, in its turn,
+ * causes the scenario to be deemed wrongly symmetric in case
+ * bfqq's weight would have been the only weight making the
+ * scenario asymmetric. On the bright side, no unbalance will
+ * however occur when bfqq becomes inactive again (the
+ * invocation of this function is triggered by an activation
+ * of queue). In fact, bfq_weights_tree_remove does nothing
+ * if !bfqq->weight_counter.
*/
if (unlikely(!bfqq->weight_counter))
return;
*/
return;
- new_budget = max_t(unsigned long, bfqq->max_budget,
- bfq_serv_to_charge(next_rq, bfqq));
+ new_budget = max_t(unsigned long,
+ max_t(unsigned long, bfqq->max_budget,
+ bfq_serv_to_charge(next_rq, bfqq)),
+ entity->service);
if (entity->budget != new_budget) {
entity->budget = new_budget;
bfq_log_bfqq(bfqd, bfqq, "updated next rq: new budget %lu",
{
struct bfq_entity *entity = &bfqq->entity;
- if (bfq_bfqq_non_blocking_wait_rq(bfqq) && arrived_in_time) {
+ /*
+ * In the next compound condition, we check also whether there
+ * is some budget left, because otherwise there is no point in
+ * trying to go on serving bfqq with this same budget: bfqq
+ * would be expired immediately after being selected for
+ * service. This would only cause useless overhead.
+ */
+ if (bfq_bfqq_non_blocking_wait_rq(bfqq) && arrived_in_time &&
+ bfq_bfqq_budget_left(bfqq) > 0) {
/*
* We do not clear the flag non_blocking_wait_rq here, as
* the latter is used in bfq_activate_bfqq to signal
return NULL;
/* If there is only one backlogged queue, don't search. */
- if (bfqd->busy_queues == 1)
+ if (bfq_tot_busy_queues(bfqd) == 1)
return NULL;
in_service_bfqq = bfqd->in_service_queue;
* requests, then the request pattern is isochronous
* (see the comments on the function
* bfq_bfqq_softrt_next_start()). Thus we can compute
- * soft_rt_next_start. If, instead, the queue still
- * has outstanding requests, then we have to wait for
- * the completion of all the outstanding requests to
- * discover whether the request pattern is actually
- * isochronous.
+ * soft_rt_next_start. And we do it, unless bfqq is in
+ * interactive weight raising. We do not do it in the
+ * latter subcase, for the following reason. bfqq may
+ * be conveying the I/O needed to load a soft
+ * real-time application. Such an application will
+ * actually exhibit a soft real-time I/O pattern after
+ * it finally starts doing its job. But, if
+ * soft_rt_next_start is computed here for an
+ * interactive bfqq, and bfqq had received a lot of
+ * service before remaining with no outstanding
+ * request (likely to happen on a fast device), then
+ * soft_rt_next_start would be assigned such a high
+ * value that, for a very long time, bfqq would be
+ * prevented from being possibly considered as soft
+ * real time.
+ *
+ * If, instead, the queue still has outstanding
+ * requests, then we have to wait for the completion
+ * of all the outstanding requests to discover whether
+ * the request pattern is actually isochronous.
*/
- if (bfqq->dispatched == 0)
+ if (bfqq->dispatched == 0 &&
+ bfqq->wr_coeff != bfqd->bfq_wr_coeff)
bfqq->soft_rt_next_start =
bfq_bfqq_softrt_next_start(bfqd, bfqq);
- else {
+ else if (bfqq->dispatched > 0) {
/*
* Schedule an update of soft_rt_next_start to when
* the task may be discovered to be isochronous.
bfq_bfqq_budget_timeout(bfqq);
}
-/*
- * For a queue that becomes empty, device idling is allowed only if
- * this function returns true for the queue. As a consequence, since
- * device idling plays a critical role in both throughput boosting and
- * service guarantees, the return value of this function plays a
- * critical role in both these aspects as well.
- *
- * In a nutshell, this function returns true only if idling is
- * beneficial for throughput or, even if detrimental for throughput,
- * idling is however necessary to preserve service guarantees (low
- * latency, desired throughput distribution, ...). In particular, on
- * NCQ-capable devices, this function tries to return false, so as to
- * help keep the drives' internal queues full, whenever this helps the
- * device boost the throughput without causing any service-guarantee
- * issue.
- *
- * In more detail, the return value of this function is obtained by,
- * first, computing a number of boolean variables that take into
- * account throughput and service-guarantee issues, and, then,
- * combining these variables in a logical expression. Most of the
- * issues taken into account are not trivial. We discuss these issues
- * individually while introducing the variables.
- */
-static bool bfq_better_to_idle(struct bfq_queue *bfqq)
+static bool idling_boosts_thr_without_issues(struct bfq_data *bfqd,
+ struct bfq_queue *bfqq)
{
- struct bfq_data *bfqd = bfqq->bfqd;
bool rot_without_queueing =
!blk_queue_nonrot(bfqd->queue) && !bfqd->hw_tag,
bfqq_sequential_and_IO_bound,
- idling_boosts_thr, idling_boosts_thr_without_issues,
- idling_needed_for_service_guarantees,
- asymmetric_scenario;
-
- if (bfqd->strict_guarantees)
- return true;
-
- /*
- * Idling is performed only if slice_idle > 0. In addition, we
- * do not idle if
- * (a) bfqq is async
- * (b) bfqq is in the idle io prio class: in this case we do
- * not idle because we want to minimize the bandwidth that
- * queues in this class can steal to higher-priority queues
- */
- if (bfqd->bfq_slice_idle == 0 || !bfq_bfqq_sync(bfqq) ||
- bfq_class_idle(bfqq))
- return false;
+ idling_boosts_thr;
bfqq_sequential_and_IO_bound = !BFQQ_SEEKY(bfqq) &&
bfq_bfqq_IO_bound(bfqq) && bfq_bfqq_has_short_ttime(bfqq);
bfqq_sequential_and_IO_bound);
/*
- * The value of the next variable,
- * idling_boosts_thr_without_issues, is equal to that of
+ * The return value of this function is equal to that of
* idling_boosts_thr, unless a special case holds. In this
* special case, described below, idling may cause problems to
* weight-raised queues.
* which enqueue several requests in advance, and further
* reorder internally-queued requests.
*
- * For this reason, we force to false the value of
- * idling_boosts_thr_without_issues if there are weight-raised
- * busy queues. In this case, and if bfqq is not weight-raised,
- * this guarantees that the device is not idled for bfqq (if,
- * instead, bfqq is weight-raised, then idling will be
- * guaranteed by another variable, see below). Combined with
- * the timestamping rules of BFQ (see [1] for details), this
- * behavior causes bfqq, and hence any sync non-weight-raised
- * queue, to get a lower number of requests served, and thus
- * to ask for a lower number of requests from the request
- * pool, before the busy weight-raised queues get served
- * again. This often mitigates starvation problems in the
- * presence of heavy write workloads and NCQ, thereby
- * guaranteeing a higher application and system responsiveness
- * in these hostile scenarios.
+ * For this reason, we force to false the return value if
+ * there are weight-raised busy queues. In this case, and if
+ * bfqq is not weight-raised, this guarantees that the device
+ * is not idled for bfqq (if, instead, bfqq is weight-raised,
+ * then idling will be guaranteed by another variable, see
+ * below). Combined with the timestamping rules of BFQ (see
+ * [1] for details), this behavior causes bfqq, and hence any
+ * sync non-weight-raised queue, to get a lower number of
+ * requests served, and thus to ask for a lower number of
+ * requests from the request pool, before the busy
+ * weight-raised queues get served again. This often mitigates
+ * starvation problems in the presence of heavy write
+ * workloads and NCQ, thereby guaranteeing a higher
+ * application and system responsiveness in these hostile
+ * scenarios.
*/
- idling_boosts_thr_without_issues = idling_boosts_thr &&
+ return idling_boosts_thr &&
bfqd->wr_busy_queues == 0;
+}
+static bool idling_needed_for_service_guarantees(struct bfq_data *bfqd,
+ struct bfq_queue *bfqq)
+{
/*
- * There is then a case where idling must be performed not
- * for throughput concerns, but to preserve service
- * guarantees.
+ * There is a case where idling must be performed not for
+ * throughput concerns, but to preserve service guarantees.
*
* To introduce this case, we can note that allowing the drive
- * to enqueue more than one request at a time, and hence
+ * to enqueue more than one request at a time, and thereby
* delegating de facto final scheduling decisions to the
* drive's internal scheduler, entails loss of control on the
* actual request service order. In particular, the critical
* to let requests be served in the desired order until all
* the requests already queued in the device have been served.
*/
- asymmetric_scenario = (bfqq->wr_coeff > 1 &&
- bfqd->wr_busy_queues < bfqd->busy_queues) ||
+ bool asymmetric_scenario = (bfqq->wr_coeff > 1 &&
+ bfqd->wr_busy_queues <
+ bfq_tot_busy_queues(bfqd)) ||
!bfq_symmetric_scenario(bfqd);
/*
* now establish when idling is actually needed to preserve
* service guarantees.
*/
- idling_needed_for_service_guarantees =
- asymmetric_scenario && !bfq_bfqq_in_large_burst(bfqq);
+ return asymmetric_scenario && !bfq_bfqq_in_large_burst(bfqq);
+}
+
+/*
+ * For a queue that becomes empty, device idling is allowed only if
+ * this function returns true for that queue. As a consequence, since
+ * device idling plays a critical role for both throughput boosting
+ * and service guarantees, the return value of this function plays a
+ * critical role as well.
+ *
+ * In a nutshell, this function returns true only if idling is
+ * beneficial for throughput or, even if detrimental for throughput,
+ * idling is however necessary to preserve service guarantees (low
+ * latency, desired throughput distribution, ...). In particular, on
+ * NCQ-capable devices, this function tries to return false, so as to
+ * help keep the drives' internal queues full, whenever this helps the
+ * device boost the throughput without causing any service-guarantee
+ * issue.
+ *
+ * Most of the issues taken into account to get the return value of
+ * this function are not trivial. We discuss these issues in the two
+ * functions providing the main pieces of information needed by this
+ * function.
+ */
+static bool bfq_better_to_idle(struct bfq_queue *bfqq)
+{
+ struct bfq_data *bfqd = bfqq->bfqd;
+ bool idling_boosts_thr_with_no_issue, idling_needed_for_service_guar;
+
+ if (unlikely(bfqd->strict_guarantees))
+ return true;
+
+ /*
+ * Idling is performed only if slice_idle > 0. In addition, we
+ * do not idle if
+ * (a) bfqq is async
+ * (b) bfqq is in the idle io prio class: in this case we do
+ * not idle because we want to minimize the bandwidth that
+ * queues in this class can steal to higher-priority queues
+ */
+ if (bfqd->bfq_slice_idle == 0 || !bfq_bfqq_sync(bfqq) ||
+ bfq_class_idle(bfqq))
+ return false;
+
+ idling_boosts_thr_with_no_issue =
+ idling_boosts_thr_without_issues(bfqd, bfqq);
+
+ idling_needed_for_service_guar =
+ idling_needed_for_service_guarantees(bfqd, bfqq);
/*
- * We have now all the components we need to compute the
+ * We have now the two components we need to compute the
* return value of the function, which is true only if idling
* either boosts the throughput (without issues), or is
* necessary to preserve service guarantees.
*/
- return idling_boosts_thr_without_issues ||
- idling_needed_for_service_guarantees;
+ return idling_boosts_thr_with_no_issue ||
+ idling_needed_for_service_guar;
}
/*
* belongs to CLASS_IDLE and other queues are waiting for
* service.
*/
- if (!(bfqd->busy_queues > 1 && bfq_class_idle(bfqq)))
+ if (!(bfq_tot_busy_queues(bfqd) > 1 && bfq_class_idle(bfqq)))
goto return_rq;
bfq_bfqq_expire(bfqd, bfqq, false, BFQQE_BUDGET_EXHAUSTED);
* most a call to dispatch for nothing
*/
return !list_empty_careful(&bfqd->dispatch) ||
- bfqd->busy_queues > 0;
+ bfq_tot_busy_queues(bfqd) > 0;
}
static struct request *__bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
goto start_rq;
}
- bfq_log(bfqd, "dispatch requests: %d busy queues", bfqd->busy_queues);
+ bfq_log(bfqd, "dispatch requests: %d busy queues",
+ bfq_tot_busy_queues(bfqd));
- if (bfqd->busy_queues == 0)
+ if (bfq_tot_busy_queues(bfqd) == 0)
goto exit;
/*
* In addition, the following queue lock guarantees that
* bfqq_group(bfqq) exists as well.
*/
- spin_lock_irq(q->queue_lock);
+ spin_lock_irq(&q->queue_lock);
if (idle_timer_disabled)
/*
* Since the idle timer has been disabled,
bfqg_stats_set_start_empty_time(bfqg);
bfqg_stats_update_io_remove(bfqg, rq->cmd_flags);
}
- spin_unlock_irq(q->queue_lock);
+ spin_unlock_irq(&q->queue_lock);
}
#else
static inline void bfq_update_dispatch_stats(struct request_queue *q,
rcu_read_lock();
- bfqg = bfq_find_set_group(bfqd, bio_blkcg(bio));
+ bfqg = bfq_find_set_group(bfqd, __bio_blkcg(bio));
if (!bfqg) {
bfqq = &bfqd->oom_bfqq;
goto out;
bool waiting, idle_timer_disabled = false;
if (new_bfqq) {
- if (bic_to_bfqq(RQ_BIC(rq), 1) != bfqq)
- new_bfqq = bic_to_bfqq(RQ_BIC(rq), 1);
/*
* Release the request's reference to the old bfqq
* and make sure one is taken to the shared queue.
* In addition, the following queue lock guarantees that
* bfqq_group(bfqq) exists as well.
*/
- spin_lock_irq(q->queue_lock);
+ spin_lock_irq(&q->queue_lock);
bfqg_stats_update_io_add(bfqq_group(bfqq), bfqq, cmd_flags);
if (idle_timer_disabled)
bfqg_stats_update_idle_time(bfqq_group(bfqq));
- spin_unlock_irq(q->queue_lock);
+ spin_unlock_irq(&q->queue_lock);
}
#else
static inline void bfq_update_insert_stats(struct request_queue *q,
* isochronous, and both requisites for this condition to hold
* are now satisfied, then compute soft_rt_next_start (see the
* comments on the function bfq_bfqq_softrt_next_start()). We
- * schedule this delayed check when bfqq expires, if it still
- * has in-flight requests.
+ * do not compute soft_rt_next_start if bfqq is in interactive
+ * weight raising (see the comments in bfq_bfqq_expire() for
+ * an explanation). We schedule this delayed update when bfqq
+ * expires, if it still has in-flight requests.
*/
if (bfq_bfqq_softrt_update(bfqq) && bfqq->dispatched == 0 &&
- RB_EMPTY_ROOT(&bfqq->sort_list))
+ RB_EMPTY_ROOT(&bfqq->sort_list) &&
+ bfqq->wr_coeff != bfqd->bfq_wr_coeff)
bfqq->soft_rt_next_start =
bfq_bfqq_softrt_next_start(bfqd, bfqq);
}
eq->elevator_data = bfqd;
- spin_lock_irq(q->queue_lock);
+ spin_lock_irq(&q->queue_lock);
q->elevator = eq;
- spin_unlock_irq(q->queue_lock);
+ spin_unlock_irq(&q->queue_lock);
/*
* Our fallback bfqq if bfq_find_alloc_queue() runs into OOM issues.
};
static struct elevator_type iosched_bfq_mq = {
- .ops.mq = {
+ .ops = {
.limit_depth = bfq_limit_depth,
.prepare_request = bfq_prepare_request,
.requeue_request = bfq_finish_requeue_request,
.exit_sched = bfq_exit_queue,
},
- .uses_mq = true,
.icq_size = sizeof(struct bfq_io_cq),
.icq_align = __alignof__(struct bfq_io_cq),
.elevator_attrs = bfq_attrs,