@@ -1721,6 +1721,123 @@ static void bfq_add_request(struct request *rq)
bfqq->queued[rq_is_sync(rq)]++;
bfqd->queued++;
+ if (RB_EMPTY_ROOT(&bfqq->sort_list) && bfq_bfqq_sync(bfqq)) {
+ /*
+ * Periodically reset inject limit, to make sure that
+ * the latter eventually drops in case workload
+ * changes, see step (3) in the comments on
+ * bfq_update_inject_limit().
+ */
+ if (time_is_before_eq_jiffies(bfqq->decrease_time_jif +
+ msecs_to_jiffies(1000))) {
+ /* invalidate baseline total service time */
+ bfqq->last_serv_time_ns = 0;
+
+ /*
+ * Reset pointer in case we are waiting for
+ * some request completion.
+ */
+ bfqd->waited_rq = NULL;
+
+ /*
+ * If bfqq has a short think time, then start
+ * by setting the inject limit to 0
+ * prudentially, because the service time of
+ * an injected I/O request may be higher than
+ * the think time of bfqq, and therefore, if
+ * one request was injected when bfqq remains
+ * empty, this injected request might delay
+ * the service of the next I/O request for
+ * bfqq significantly. In case bfqq can
+ * actually tolerate some injection, then the
+ * adaptive update will however raise the
+ * limit soon. This lucky circumstance holds
+ * exactly because bfqq has a short think
+ * time, and thus, after remaining empty, is
+ * likely to get new I/O enqueued---and then
+ * completed---before being expired. This is
+ * the very pattern that gives the
+ * limit-update algorithm the chance to
+ * measure the effect of injection on request
+ * service times, and then to update the limit
+ * accordingly.
+ *
+ * On the opposite end, if bfqq has a long
+ * think time, then start directly by 1,
+ * because:
+ * a) on the bright side, keeping at most one
+ * request in service in the drive is unlikely
+ * to cause any harm to the latency of bfqq's
+ * requests, as the service time of a single
+ * request is likely to be lower than the
+ * think time of bfqq;
+ * b) on the downside, after becoming empty,
+ * bfqq is likely to expire before getting its
+ * next request. With this request arrival
+ * pattern, it is very hard to sample total
+ * service times and update the inject limit
+ * accordingly (see comments on
+ * bfq_update_inject_limit()). So the limit is
+ * likely to be never, or at least seldom,
+ * updated. As a consequence, by setting the
+ * limit to 1, we avoid that no injection ever
+ * occurs with bfqq. On the downside, this
+ * proactive step further reduces chances to
+ * actually compute the baseline total service
+ * time. Thus it reduces chances to execute the
+ * limit-update algorithm and possibly raise the
+ * limit to more than 1.
+ */
+ if (bfq_bfqq_has_short_ttime(bfqq))
+ bfqq->inject_limit = 0;
+ else
+ bfqq->inject_limit = 1;
+ bfqq->decrease_time_jif = jiffies;
+ }
+
+ /*
+ * The following conditions must hold to setup a new
+ * sampling of total service time, and then a new
+ * update of the inject limit:
+ * - bfqq is in service, because the total service
+ * time is evaluated only for the I/O requests of
+ * the queues in service;
+ * - this is the right occasion to compute or to
+ * lower the baseline total service time, because
+ * there are actually no requests in the drive,
+ * or
+ * the baseline total service time is available, and
+ * this is the right occasion to compute the other
+ * quantity needed to update the inject limit, i.e.,
+ * the total service time caused by the amount of
+ * injection allowed by the current value of the
+ * limit. It is the right occasion because injection
+ * has actually been performed during the service
+ * hole, and there are still in-flight requests,
+ * which are very likely to be exactly the injected
+ * requests, or part of them;
+ * - the minimum interval for sampling the total
+ * service time and updating the inject limit has
+ * elapsed.
+ */
+ if (bfqq == bfqd->in_service_queue &&
+ (bfqd->rq_in_driver == 0 ||
+ (bfqq->last_serv_time_ns > 0 &&
+ bfqd->rqs_injected && bfqd->rq_in_driver > 0)) &&
+ time_is_before_eq_jiffies(bfqq->decrease_time_jif +
+ msecs_to_jiffies(100))) {
+ bfqd->last_empty_occupied_ns = ktime_get_ns();
+ /*
+ * Start the state machine for measuring the
+ * total service time of rq: setting
+ * wait_dispatch will cause bfqd->waited_rq to
+ * be set when rq will be dispatched.
+ */
+ bfqd->wait_dispatch = true;
+ bfqd->rqs_injected = false;
+ }
+ }
+
elv_rb_add(&bfqq->sort_list, rq);
/*
@@ -2566,6 +2683,8 @@ static void bfq_arm_slice_timer(struct bfq_data *bfqd)
sl = max_t(u32, sl, 20ULL * NSEC_PER_MSEC);
bfqd->last_idling_start = ktime_get();
+ bfqd->last_idling_start_jiffies = jiffies;
+
hrtimer_start(&bfqd->idle_slice_timer, ns_to_ktime(sl),
HRTIMER_MODE_REL);
bfqg_stats_set_start_idle_time(bfqq_group(bfqq));
@@ -3240,13 +3359,6 @@ static unsigned long bfq_bfqq_softrt_next_start(struct bfq_data *bfqd,
jiffies + nsecs_to_jiffies(bfqq->bfqd->bfq_slice_idle) + 4);
}
-static bool bfq_bfqq_injectable(struct bfq_queue *bfqq)
-{
- return BFQQ_SEEKY(bfqq) && bfqq->wr_coeff == 1 &&
- blk_queue_nonrot(bfqq->bfqd->queue) &&
- bfqq->bfqd->hw_tag;
-}
-
/**
* bfq_bfqq_expire - expire a queue.
* @bfqd: device owning the queue.
@@ -3361,6 +3473,14 @@ void bfq_bfqq_expire(struct bfq_data *bfqd,
"expire (%d, slow %d, num_disp %d, short_ttime %d)", reason,
slow, bfqq->dispatched, bfq_bfqq_has_short_ttime(bfqq));
+ /*
+ * bfqq expired, so no total service time needs to be computed
+ * any longer: reset state machine for measuring total service
+ * times.
+ */
+ bfqd->rqs_injected = bfqd->wait_dispatch = false;
+ bfqd->waited_rq = NULL;
+
/*
* Increase, decrease or leave budget unchanged according to
* reason.
@@ -3372,8 +3492,6 @@ void bfq_bfqq_expire(struct bfq_data *bfqd,
if (ref == 1) /* bfqq is gone, no more actions on it */
return;
- bfqq->injected_service = 0;
-
/* mark bfqq as waiting a request only if a bic still points to it */
if (!bfq_bfqq_busy(bfqq) &&
reason != BFQQE_BUDGET_TIMEOUT &&
@@ -3767,26 +3885,98 @@ static bool bfq_bfqq_must_idle(struct bfq_queue *bfqq)
return RB_EMPTY_ROOT(&bfqq->sort_list) && bfq_better_to_idle(bfqq);
}
-static struct bfq_queue *bfq_choose_bfqq_for_injection(struct bfq_data *bfqd)
+/*
+ * This function chooses the queue from which to pick the next extra
+ * I/O request to inject, if it finds a compatible queue. See the
+ * comments on bfq_update_inject_limit() for details on the injection
+ * mechanism, and for the definitions of the quantities mentioned
+ * below.
+ */
+static struct bfq_queue *
+bfq_choose_bfqq_for_injection(struct bfq_data *bfqd)
{
- struct bfq_queue *bfqq;
+ struct bfq_queue *bfqq, *in_serv_bfqq = bfqd->in_service_queue;
+ unsigned int limit = in_serv_bfqq->inject_limit;
+ /*
+ * If
+ * - bfqq is not weight-raised and therefore does not carry
+ * time-critical I/O,
+ * or
+ * - regardless of whether bfqq is weight-raised, bfqq has
+ * however a long think time, during which it can absorb the
+ * effect of an appropriate number of extra I/O requests
+ * from other queues (see bfq_update_inject_limit for
+ * details on the computation of this number);
+ * then injection can be performed without restrictions.
+ */
+ bool in_serv_always_inject = in_serv_bfqq->wr_coeff == 1 ||
+ !bfq_bfqq_has_short_ttime(in_serv_bfqq);
/*
- * A linear search; but, with a high probability, very few
- * steps are needed to find a candidate queue, i.e., a queue
- * with enough budget left for its next request. In fact:
+ * If
+ * - the baseline total service time could not be sampled yet,
+ * so the inject limit happens to be still 0, and
+ * - a lot of time has elapsed since the plugging of I/O
+ * dispatching started, so drive speed is being wasted
+ * significantly;
+ * then temporarily raise inject limit to one request.
+ */
+ if (limit == 0 && in_serv_bfqq->last_serv_time_ns == 0 &&
+ bfq_bfqq_wait_request(in_serv_bfqq) &&
+ time_is_before_eq_jiffies(bfqd->last_idling_start_jiffies +
+ bfqd->bfq_slice_idle)
+ )
+ limit = 1;
+
+ if (bfqd->rq_in_driver >= limit)
+ return NULL;
+
+ /*
+ * Linear search of the source queue for injection; but, with
+ * a high probability, very few steps are needed to find a
+ * candidate queue, i.e., a queue with enough budget left for
+ * its next request. In fact:
* - BFQ dynamically updates the budget of every queue so as
* to accommodate the expected backlog of the queue;
* - if a queue gets all its requests dispatched as injected
* service, then the queue is removed from the active list
- * (and re-added only if it gets new requests, but with
- * enough budget for its new backlog).
+ * (and re-added only if it gets new requests, but then it
+ * is assigned again enough budget for its new backlog).
*/
list_for_each_entry(bfqq, &bfqd->active_list, bfqq_list)
if (!RB_EMPTY_ROOT(&bfqq->sort_list) &&
+ (in_serv_always_inject || bfqq->wr_coeff > 1) &&
bfq_serv_to_charge(bfqq->next_rq, bfqq) <=
- bfq_bfqq_budget_left(bfqq))
- return bfqq;
+ bfq_bfqq_budget_left(bfqq)) {
+ /*
+ * Allow for only one large in-flight request
+ * on non-rotational devices, for the
+ * following reason. On non-rotationl drives,
+ * large requests take much longer than
+ * smaller requests to be served. In addition,
+ * the drive prefers to serve large requests
+ * w.r.t. to small ones, if it can choose. So,
+ * having more than one large requests queued
+ * in the drive may easily make the next first
+ * request of the in-service queue wait for so
+ * long to break bfqq's service guarantees. On
+ * the bright side, large requests let the
+ * drive reach a very high throughput, even if
+ * there is only one in-flight large request
+ * at a time.
+ */
+ if (blk_queue_nonrot(bfqd->queue) &&
+ blk_rq_sectors(bfqq->next_rq) >=
+ BFQQ_SECT_THR_NONROT)
+ limit = min_t(unsigned int, 1, limit);
+ else
+ limit = in_serv_bfqq->inject_limit;
+
+ if (bfqd->rq_in_driver < limit) {
+ bfqd->rqs_injected = true;
+ return bfqq;
+ }
+ }
return NULL;
}
@@ -3873,14 +4063,32 @@ static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd)
* for a new request, or has requests waiting for a completion and
* may idle after their completion, then keep it anyway.
*
- * Yet, to boost throughput, inject service from other queues if
- * possible.
+ * Yet, inject service from other queues if it boosts
+ * throughput and is possible.
*/
if (bfq_bfqq_wait_request(bfqq) ||
(bfqq->dispatched != 0 && bfq_better_to_idle(bfqq))) {
- if (bfq_bfqq_injectable(bfqq) &&
- bfqq->injected_service * bfqq->inject_coeff <
- bfqq->entity.service * 10)
+ struct bfq_queue *async_bfqq =
+ bfqq->bic && bfqq->bic->bfqq[0] &&
+ bfq_bfqq_busy(bfqq->bic->bfqq[0]) ?
+ bfqq->bic->bfqq[0] : NULL;
+
+ /*
+ * If the process associated with bfqq has also async
+ * I/O pending, then inject it
+ * unconditionally. Injecting I/O from the same
+ * process can cause no harm to the process. On the
+ * contrary, it can only increase bandwidth and reduce
+ * latency for the process.
+ */
+ if (async_bfqq &&
+ icq_to_bic(async_bfqq->next_rq->elv.icq) == bfqq->bic &&
+ bfq_serv_to_charge(async_bfqq->next_rq, async_bfqq) <=
+ bfq_bfqq_budget_left(async_bfqq))
+ bfqq = bfqq->bic->bfqq[0];
+ else if (!idling_boosts_thr_without_issues(bfqd, bfqq) &&
+ (bfqq->wr_coeff == 1 || bfqd->wr_busy_queues > 1 ||
+ !bfq_bfqq_has_short_ttime(bfqq)))
bfqq = bfq_choose_bfqq_for_injection(bfqd);
else
bfqq = NULL;
@@ -3972,15 +4180,15 @@ static struct request *bfq_dispatch_rq_from_bfqq(struct bfq_data *bfqd,
bfq_bfqq_served(bfqq, service_to_charge);
- bfq_dispatch_remove(bfqd->queue, rq);
+ if (bfqq == bfqd->in_service_queue && bfqd->wait_dispatch) {
+ bfqd->wait_dispatch = false;
+ bfqd->waited_rq = rq;
+ }
- if (bfqq != bfqd->in_service_queue) {
- if (likely(bfqd->in_service_queue))
- bfqd->in_service_queue->injected_service +=
- bfq_serv_to_charge(rq, bfqq);
+ bfq_dispatch_remove(bfqd->queue, rq);
+ if (bfqq != bfqd->in_service_queue)
goto return_rq;
- }
/*
* If weight raising has to terminate for bfqq, then next
@@ -4411,13 +4619,6 @@ static void bfq_init_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
bfq_mark_bfqq_has_short_ttime(bfqq);
bfq_mark_bfqq_sync(bfqq);
bfq_mark_bfqq_just_created(bfqq);
- /*
- * Aggressively inject a lot of service: up to 90%.
- * This coefficient remains constant during bfqq life,
- * but this behavior might be changed, after enough
- * testing and tuning.
- */
- bfqq->inject_coeff = 1;
} else
bfq_clear_bfqq_sync(bfqq);
@@ -4976,6 +5177,147 @@ static void bfq_finish_requeue_request_body(struct bfq_queue *bfqq)
bfq_put_queue(bfqq);
}
+/*
+ * The processes associated with bfqq may happen to generate their
+ * cumulative I/O at a lower rate than the rate at which the device
+ * could serve the same I/O. This is rather probable, e.g., if only
+ * one process is associated with bfqq and the device is an SSD. It
+ * results in bfqq becoming often empty while in service. In this
+ * respect, if BFQ is allowed to switch to another queue when bfqq
+ * remains empty, then the device goes on being fed with I/O requests,
+ * and the throughput is not affected. In contrast, if BFQ is not
+ * allowed to switch to another queue---because bfqq is sync and
+ * I/O-dispatch needs to be plugged while bfqq is temporarily
+ * empty---then, during the service of bfqq, there will be frequent
+ * "service holes", i.e., time intervals during which bfqq gets empty
+ * and the device can only consume the I/O already queued in its
+ * hardware queues. During service holes, the device may even get to
+ * remaining idle. In the end, during the service of bfqq, the device
+ * is driven at a lower speed than the one it can reach with the kind
+ * of I/O flowing through bfqq.
+ *
+ * To counter this loss of throughput, BFQ implements a "request
+ * injection mechanism", which tries to fill the above service holes
+ * with I/O requests taken from other queues. The hard part in this
+ * mechanism is finding the right amount of I/O to inject, so as to
+ * both boost throughput and not break bfqq's bandwidth and latency
+ * guarantees. In this respect, the mechanism maintains a per-queue
+ * inject limit, computed as below. While bfqq is empty, the injection
+ * mechanism dispatches extra I/O requests only until the total number
+ * of I/O requests in flight---i.e., already dispatched but not yet
+ * completed---remains lower than this limit.
+ *
+ * A first definition comes in handy to introduce the algorithm by
+ * which the inject limit is computed. We define as first request for
+ * bfqq, an I/O request for bfqq that arrives while bfqq is in
+ * service, and causes bfqq to switch from empty to non-empty. The
+ * algorithm updates the limit as a function of the effect of
+ * injection on the service times of only the first requests of
+ * bfqq. The reason for this restriction is that these are the
+ * requests whose service time is affected most, because they are the
+ * first to arrive after injection possibly occurred.
+ *
+ * To evaluate the effect of injection, the algorithm measures the
+ * "total service time" of first requests. We define as total service
+ * time of an I/O request, the time that elapses since when the
+ * request is enqueued into bfqq, to when it is completed. This
+ * quantity allows the whole effect of injection to be measured. It is
+ * easy to see why. Suppose that some requests of other queues are
+ * actually injected while bfqq is empty, and that a new request R
+ * then arrives for bfqq. If the device does start to serve all or
+ * part of the injected requests during the service hole, then,
+ * because of this extra service, it may delay the next invocation of
+ * the dispatch hook of BFQ. Then, even after R gets eventually
+ * dispatched, the device may delay the actual service of R if it is
+ * still busy serving the extra requests, or if it decides to serve,
+ * before R, some extra request still present in its queues. As a
+ * conclusion, the cumulative extra delay caused by injection can be
+ * easily evaluated by just comparing the total service time of first
+ * requests with and without injection.
+ *
+ * The limit-update algorithm works as follows. On the arrival of a
+ * first request of bfqq, the algorithm measures the total time of the
+ * request only if one of the three cases below holds, and, for each
+ * case, it updates the limit as described below:
+ *
+ * (1) If there is no in-flight request. This gives a baseline for the
+ * total service time of the requests of bfqq. If the baseline has
+ * not been computed yet, then, after computing it, the limit is
+ * set to 1, to start boosting throughput, and to prepare the
+ * ground for the next case. If the baseline has already been
+ * computed, then it is updated, in case it results to be lower
+ * than the previous value.
+ *
+ * (2) If the limit is higher than 0 and there are in-flight
+ * requests. By comparing the total service time in this case with
+ * the above baseline, it is possible to know at which extent the
+ * current value of the limit is inflating the total service
+ * time. If the inflation is below a certain threshold, then bfqq
+ * is assumed to be suffering from no perceivable loss of its
+ * service guarantees, and the limit is even tentatively
+ * increased. If the inflation is above the threshold, then the
+ * limit is decreased. Due to the lack of any hysteresis, this
+ * logic makes the limit oscillate even in steady workload
+ * conditions. Yet we opted for it, because it is fast in reaching
+ * the best value for the limit, as a function of the current I/O
+ * workload. To reduce oscillations, this step is disabled for a
+ * short time interval after the limit happens to be decreased.
+ *
+ * (3) Periodically, after resetting the limit, to make sure that the
+ * limit eventually drops in case the workload changes. This is
+ * needed because, after the limit has gone safely up for a
+ * certain workload, it is impossible to guess whether the
+ * baseline total service time may have changed, without measuring
+ * it again without injection. A more effective version of this
+ * step might be to just sample the baseline, by interrupting
+ * injection only once, and then to reset/lower the limit only if
+ * the total service time with the current limit does happen to be
+ * too large.
+ *
+ * More details on each step are provided in the comments on the
+ * pieces of code that implement these steps: the branch handling the
+ * transition from empty to non empty in bfq_add_request(), the branch
+ * handling injection in bfq_select_queue(), and the function
+ * bfq_choose_bfqq_for_injection(). These comments also explain some
+ * exceptions, made by the injection mechanism in some special cases.
+ */
+static void bfq_update_inject_limit(struct bfq_data *bfqd,
+ struct bfq_queue *bfqq)
+{
+ u64 tot_time_ns = ktime_get_ns() - bfqd->last_empty_occupied_ns;
+ unsigned int old_limit = bfqq->inject_limit;
+
+ if (bfqq->last_serv_time_ns > 0) {
+ u64 threshold = (bfqq->last_serv_time_ns * 3)>>1;
+
+ if (tot_time_ns >= threshold && old_limit > 0) {
+ bfqq->inject_limit--;
+ bfqq->decrease_time_jif = jiffies;
+ } else if (tot_time_ns < threshold &&
+ old_limit < bfqd->max_rq_in_driver<<1)
+ bfqq->inject_limit++;
+ }
+
+ /*
+ * Either we still have to compute the base value for the
+ * total service time, and there seem to be the right
+ * conditions to do it, or we can lower the last base value
+ * computed.
+ */
+ if ((bfqq->last_serv_time_ns == 0 && bfqd->rq_in_driver == 0) ||
+ tot_time_ns < bfqq->last_serv_time_ns) {
+ bfqq->last_serv_time_ns = tot_time_ns;
+ /*
+ * Now we certainly have a base value: make sure we
+ * start trying injection.
+ */
+ bfqq->inject_limit = max_t(unsigned int, 1, old_limit);
+ }
+
+ /* update complete, not waiting for any request completion any longer */
+ bfqd->waited_rq = NULL;
+}
+
/*
* Handle either a requeue or a finish for rq. The things to do are
* the same in both cases: all references to rq are to be dropped. In
@@ -5020,6 +5362,9 @@ static void bfq_finish_requeue_request(struct request *rq)
spin_lock_irqsave(&bfqd->lock, flags);
+ if (rq == bfqd->waited_rq)
+ bfq_update_inject_limit(bfqd, bfqq);
+
bfq_completed_request(bfqq, bfqd);
bfq_finish_requeue_request_body(bfqq);
@@ -240,6 +240,13 @@ struct bfq_queue {
/* next ioprio and ioprio class if a change is in progress */
unsigned short new_ioprio, new_ioprio_class;
+ /* last total-service-time sample, see bfq_update_inject_limit() */
+ u64 last_serv_time_ns;
+ /* limit for request injection */
+ unsigned int inject_limit;
+ /* last time the inject limit has been decreased, in jiffies */
+ unsigned long decrease_time_jif;
+
/*
* Shared bfq_queue if queue is cooperating with one or more
* other queues.
@@ -357,29 +364,6 @@ struct bfq_queue {
/* max service rate measured so far */
u32 max_service_rate;
- /*
- * Ratio between the service received by bfqq while it is in
- * service, and the cumulative service (of requests of other
- * queues) that may be injected while bfqq is empty but still
- * in service. To increase precision, the coefficient is
- * measured in tenths of unit. Here are some example of (1)
- * ratios, (2) resulting percentages of service injected
- * w.r.t. to the total service dispatched while bfqq is in
- * service, and (3) corresponding values of the coefficient:
- * 1 (50%) -> 10
- * 2 (33%) -> 20
- * 10 (9%) -> 100
- * 9.9 (9%) -> 99
- * 1.5 (40%) -> 15
- * 0.5 (66%) -> 5
- * 0.1 (90%) -> 1
- *
- * So, if the coefficient is lower than 10, then
- * injected service is more than bfqq service.
- */
- unsigned int inject_coeff;
- /* amount of service injected in current service slot */
- unsigned int injected_service;
};
/**
@@ -544,6 +528,26 @@ struct bfq_data {
/* time of last request completion (ns) */
u64 last_completion;
+ /* time of last transition from empty to non-empty (ns) */
+ u64 last_empty_occupied_ns;
+
+ /*
+ * Flag set to activate the sampling of the total service time
+ * of a just-arrived first I/O request (see
+ * bfq_update_inject_limit()). This will cause the setting of
+ * waited_rq when the request is finally dispatched.
+ */
+ bool wait_dispatch;
+ /*
+ * If set, then bfq_update_inject_limit() is invoked when
+ * waited_rq is eventually completed.
+ */
+ struct request *waited_rq;
+ /*
+ * True if some request has been injected during the last service hole.
+ */
+ bool rqs_injected;
+
/* time of first rq dispatch in current observation interval (ns) */
u64 first_dispatch;
/* time of last rq dispatch in current observation interval (ns) */
@@ -553,6 +557,7 @@ struct bfq_data {
ktime_t last_budget_start;
/* beginning of the last idle slice */
ktime_t last_idling_start;
+ unsigned long last_idling_start_jiffies;
/* number of samples in current observation interval */
int peak_rate_samples;