summaryrefslogtreecommitdiff
path: root/block/bfq-iosched.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2021-02-21 11:02:48 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2021-02-21 11:02:48 -0800
commit582cd91f69de8e44857cb610ebca661dac8656b7 (patch)
tree0d680db02a5c236ee87b408b3f13ce33ebaca907 /block/bfq-iosched.c
parentbd018bbaa58640da786d4289563e71c5ef3938c7 (diff)
parentf885056a48ccf4ad4332def91e973f3993fa8695 (diff)
Merge tag 'for-5.12/block-2021-02-17' of git://git.kernel.dk/linux-block
Pull core block updates from Jens Axboe: "Another nice round of removing more code than what is added, mostly due to Christoph's relentless pursuit of tech debt removal/cleanups. This pull request contains: - Two series of BFQ improvements (Paolo, Jan, Jia) - Block iov_iter improvements (Pavel) - bsg error path fix (Pan) - blk-mq scheduler improvements (Jan) - -EBUSY discard fix (Jan) - bvec allocation improvements (Ming, Christoph) - bio allocation and init improvements (Christoph) - Store bdev pointer in bio instead of gendisk + partno (Christoph) - Block trace point cleanups (Christoph) - hard read-only vs read-only split (Christoph) - Block based swap cleanups (Christoph) - Zoned write granularity support (Damien) - Various fixes/tweaks (Chunguang, Guoqing, Lei, Lukas, Huhai)" * tag 'for-5.12/block-2021-02-17' of git://git.kernel.dk/linux-block: (104 commits) mm: simplify swapdev_block sd_zbc: clear zone resources for non-zoned case block: introduce blk_queue_clear_zone_settings() zonefs: use zone write granularity as block size block: introduce zone_write_granularity limit block: use blk_queue_set_zoned in add_partition() nullb: use blk_queue_set_zoned() to setup zoned devices nvme: cleanup zone information initialization block: document zone_append_max_bytes attribute block: use bi_max_vecs to find the bvec pool md/raid10: remove dead code in reshape_request block: mark the bio as cloned in bio_iov_bvec_set block: set BIO_NO_PAGE_REF in bio_iov_bvec_set block: remove a layer of indentation in bio_iov_iter_get_pages block: turn the nr_iovecs argument to bio_alloc* into an unsigned short block: remove the 1 and 4 vec bvec_slabs entries block: streamline bvec_alloc block: factor out a bvec_alloc_gfp helper block: move struct biovec_slab to bio.c block: reuse BIO_INLINE_VECS for integrity bvecs ...
Diffstat (limited to 'block/bfq-iosched.c')
-rw-r--r--block/bfq-iosched.c445
1 files changed, 276 insertions, 169 deletions
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 9e81d1052091..b398dde53af9 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -158,7 +158,6 @@ BFQ_BFQQ_FNS(in_large_burst);
BFQ_BFQQ_FNS(coop);
BFQ_BFQQ_FNS(split_coop);
BFQ_BFQQ_FNS(softrt_update);
-BFQ_BFQQ_FNS(has_waker);
#undef BFQ_BFQQ_FNS \
/* Expiration time of sync (0) and async (1) requests, in ns. */
@@ -1024,9 +1023,16 @@ bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_data *bfqd,
else
bfq_clear_bfqq_IO_bound(bfqq);
+ bfqq->last_serv_time_ns = bic->saved_last_serv_time_ns;
+ bfqq->inject_limit = bic->saved_inject_limit;
+ bfqq->decrease_time_jif = bic->saved_decrease_time_jif;
+
bfqq->entity.new_weight = bic->saved_weight;
bfqq->ttime = bic->saved_ttime;
+ bfqq->io_start_time = bic->saved_io_start_time;
+ bfqq->tot_idle_time = bic->saved_tot_idle_time;
bfqq->wr_coeff = bic->saved_wr_coeff;
+ bfqq->service_from_wr = bic->saved_service_from_wr;
bfqq->wr_start_at_switch_to_srt = bic->saved_wr_start_at_switch_to_srt;
bfqq->last_wr_start_finish = bic->saved_last_wr_start_finish;
bfqq->wr_cur_max_time = bic->saved_wr_cur_max_time;
@@ -1647,6 +1653,8 @@ static bool bfq_bfqq_higher_class_or_weight(struct bfq_queue *bfqq,
return bfqq_weight > in_serv_weight;
}
+static bool bfq_better_to_idle(struct bfq_queue *bfqq);
+
static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd,
struct bfq_queue *bfqq,
int old_wr_coeff,
@@ -1671,15 +1679,19 @@ static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd,
* - it is sync,
* - it does not belong to a large burst,
* - it has been idle for enough time or is soft real-time,
- * - is linked to a bfq_io_cq (it is not shared in any sense).
+ * - is linked to a bfq_io_cq (it is not shared in any sense),
+ * - has a default weight (otherwise we assume the user wanted
+ * to control its weight explicitly)
*/
in_burst = bfq_bfqq_in_large_burst(bfqq);
soft_rt = bfqd->bfq_wr_max_softrt_rate > 0 &&
!BFQQ_TOTALLY_SEEKY(bfqq) &&
!in_burst &&
time_is_before_jiffies(bfqq->soft_rt_next_start) &&
- bfqq->dispatched == 0;
- *interactive = !in_burst && idle_for_long_time;
+ bfqq->dispatched == 0 &&
+ bfqq->entity.new_weight == 40;
+ *interactive = !in_burst && idle_for_long_time &&
+ bfqq->entity.new_weight == 40;
wr_or_deserves_wr = bfqd->low_latency &&
(bfqq->wr_coeff > 1 ||
(bfq_bfqq_sync(bfqq) &&
@@ -1717,17 +1729,6 @@ static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd,
bfq_clear_bfqq_just_created(bfqq);
-
- if (!bfq_bfqq_IO_bound(bfqq)) {
- if (arrived_in_time) {
- bfqq->requests_within_timer++;
- if (bfqq->requests_within_timer >=
- bfqd->bfq_requests_within_timer)
- bfq_mark_bfqq_IO_bound(bfqq);
- } else
- bfqq->requests_within_timer = 0;
- }
-
if (bfqd->low_latency) {
if (unlikely(time_is_after_jiffies(bfqq->split_time)))
/* wraparound */
@@ -1755,10 +1756,10 @@ static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd,
bfq_add_bfqq_busy(bfqd, bfqq);
/*
- * Expire in-service queue only if preemption may be needed
- * for guarantees. In particular, we care only about two
- * cases. The first is that bfqq has to recover a service
- * hole, as explained in the comments on
+ * Expire in-service queue if preemption may be needed for
+ * guarantees or throughput. As for guarantees, we care
+ * explicitly about two cases. The first is that bfqq has to
+ * recover a service hole, as explained in the comments on
* bfq_bfqq_update_budg_for_activation(), i.e., that
* bfqq_wants_to_preempt is true. However, if bfqq does not
* carry time-critical I/O, then bfqq's bandwidth is less
@@ -1785,11 +1786,23 @@ static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd,
* timestamps of the in-service queue would need to be
* updated, and this operation is quite costly (see the
* comments on bfq_bfqq_update_budg_for_activation()).
+ *
+ * As for throughput, we ask bfq_better_to_idle() whether we
+ * still need to plug I/O dispatching. If bfq_better_to_idle()
+ * says no, then plugging is not needed any longer, either to
+ * boost throughput or to perserve service guarantees. Then
+ * the best option is to stop plugging I/O, as not doing so
+ * would certainly lower throughput. We may end up in this
+ * case if: (1) upon a dispatch attempt, we detected that it
+ * was better to plug I/O dispatch, and to wait for a new
+ * request to arrive for the currently in-service queue, but
+ * (2) this switch of bfqq to busy changes the scenario.
*/
if (bfqd->in_service_queue &&
((bfqq_wants_to_preempt &&
bfqq->wr_coeff >= bfqd->in_service_queue->wr_coeff) ||
- bfq_bfqq_higher_class_or_weight(bfqq, bfqd->in_service_queue)) &&
+ bfq_bfqq_higher_class_or_weight(bfqq, bfqd->in_service_queue) ||
+ !bfq_better_to_idle(bfqd->in_service_queue)) &&
next_queue_may_preempt(bfqd))
bfq_bfqq_expire(bfqd, bfqd->in_service_queue,
false, BFQQE_PREEMPTED);
@@ -1861,6 +1874,138 @@ static void bfq_reset_inject_limit(struct bfq_data *bfqd,
bfqq->decrease_time_jif = jiffies;
}
+static void bfq_update_io_intensity(struct bfq_queue *bfqq, u64 now_ns)
+{
+ u64 tot_io_time = now_ns - bfqq->io_start_time;
+
+ if (RB_EMPTY_ROOT(&bfqq->sort_list) && bfqq->dispatched == 0)
+ bfqq->tot_idle_time +=
+ now_ns - bfqq->ttime.last_end_request;
+
+ if (unlikely(bfq_bfqq_just_created(bfqq)))
+ return;
+
+ /*
+ * Must be busy for at least about 80% of the time to be
+ * considered I/O bound.
+ */
+ if (bfqq->tot_idle_time * 5 > tot_io_time)
+ bfq_clear_bfqq_IO_bound(bfqq);
+ else
+ bfq_mark_bfqq_IO_bound(bfqq);
+
+ /*
+ * Keep an observation window of at most 200 ms in the past
+ * from now.
+ */
+ if (tot_io_time > 200 * NSEC_PER_MSEC) {
+ bfqq->io_start_time = now_ns - (tot_io_time>>1);
+ bfqq->tot_idle_time >>= 1;
+ }
+}
+
+/*
+ * Detect whether bfqq's I/O seems synchronized with that of some
+ * other queue, i.e., whether bfqq, after remaining empty, happens to
+ * receive new I/O only right after some I/O request of the other
+ * queue has been completed. We call waker queue the other queue, and
+ * we assume, for simplicity, that bfqq may have at most one waker
+ * queue.
+ *
+ * A remarkable throughput boost can be reached by unconditionally
+ * injecting the I/O of the waker queue, every time a new
+ * bfq_dispatch_request happens to be invoked while I/O is being
+ * plugged for bfqq. In addition to boosting throughput, this
+ * unblocks bfqq's I/O, thereby improving bandwidth and latency for
+ * bfqq. Note that these same results may be achieved with the general
+ * injection mechanism, but less effectively. For details on this
+ * aspect, see the comments on the choice of the queue for injection
+ * in bfq_select_queue().
+ *
+ * Turning back to the detection of a waker queue, a queue Q is deemed
+ * as a waker queue for bfqq if, for three consecutive times, bfqq
+ * happens to become non empty right after a request of Q has been
+ * completed. In particular, on the first time, Q is tentatively set
+ * as a candidate waker queue, while on the third consecutive time
+ * that Q is detected, the field waker_bfqq is set to Q, to confirm
+ * that Q is a waker queue for bfqq. These detection steps are
+ * performed only if bfqq has a long think time, so as to make it more
+ * likely that bfqq's I/O is actually being blocked by a
+ * synchronization. This last filter, plus the above three-times
+ * requirement, make false positives less likely.
+ *
+ * NOTE
+ *
+ * The sooner a waker queue is detected, the sooner throughput can be
+ * boosted by injecting I/O from the waker queue. Fortunately,
+ * detection is likely to be actually fast, for the following
+ * reasons. While blocked by synchronization, bfqq has a long think
+ * time. This implies that bfqq's inject limit is at least equal to 1
+ * (see the comments in bfq_update_inject_limit()). So, thanks to
+ * injection, the waker queue is likely to be served during the very
+ * first I/O-plugging time interval for bfqq. This triggers the first
+ * step of the detection mechanism. Thanks again to injection, the
+ * candidate waker queue is then likely to be confirmed no later than
+ * during the next I/O-plugging interval for bfqq.
+ *
+ * ISSUE
+ *
+ * On queue merging all waker information is lost.
+ */
+static void bfq_check_waker(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+ u64 now_ns)
+{
+ if (!bfqd->last_completed_rq_bfqq ||
+ bfqd->last_completed_rq_bfqq == bfqq ||
+ bfq_bfqq_has_short_ttime(bfqq) ||
+ now_ns - bfqd->last_completion >= 4 * NSEC_PER_MSEC ||
+ bfqd->last_completed_rq_bfqq == bfqq->waker_bfqq)
+ return;
+
+ if (bfqd->last_completed_rq_bfqq !=
+ bfqq->tentative_waker_bfqq) {
+ /*
+ * First synchronization detected with a
+ * candidate waker queue, or with a different
+ * candidate waker queue from the current one.
+ */
+ bfqq->tentative_waker_bfqq =
+ bfqd->last_completed_rq_bfqq;
+ bfqq->num_waker_detections = 1;
+ } else /* Same tentative waker queue detected again */
+ bfqq->num_waker_detections++;
+
+ if (bfqq->num_waker_detections == 3) {
+ bfqq->waker_bfqq = bfqd->last_completed_rq_bfqq;
+ bfqq->tentative_waker_bfqq = NULL;
+
+ /*
+ * If the waker queue disappears, then
+ * bfqq->waker_bfqq must be reset. To
+ * this goal, we maintain in each
+ * waker queue a list, woken_list, of
+ * all the queues that reference the
+ * waker queue through their
+ * waker_bfqq pointer. When the waker
+ * queue exits, the waker_bfqq pointer
+ * of all the queues in the woken_list
+ * is reset.
+ *
+ * In addition, if bfqq is already in
+ * the woken_list of a waker queue,
+ * then, before being inserted into
+ * the woken_list of a new waker
+ * queue, bfqq must be removed from
+ * the woken_list of the old waker
+ * queue.
+ */
+ if (!hlist_unhashed(&bfqq->woken_list_node))
+ hlist_del_init(&bfqq->woken_list_node);
+ hlist_add_head(&bfqq->woken_list_node,
+ &bfqd->last_completed_rq_bfqq->woken_list);
+ }
+}
+
static void bfq_add_request(struct request *rq)
{
struct bfq_queue *bfqq = RQ_BFQQ(rq);
@@ -1868,117 +2013,14 @@ static void bfq_add_request(struct request *rq)
struct request *next_rq, *prev;
unsigned int old_wr_coeff = bfqq->wr_coeff;
bool interactive = false;
+ u64 now_ns = ktime_get_ns();
bfq_log_bfqq(bfqd, bfqq, "add_request %d", rq_is_sync(rq));
bfqq->queued[rq_is_sync(rq)]++;
bfqd->queued++;
if (RB_EMPTY_ROOT(&bfqq->sort_list) && bfq_bfqq_sync(bfqq)) {
- /*
- * Detect whether bfqq's I/O seems synchronized with
- * that of some other queue, i.e., whether bfqq, after
- * remaining empty, happens to receive new I/O only
- * right after some I/O request of the other queue has
- * been completed. We call waker queue the other
- * queue, and we assume, for simplicity, that bfqq may
- * have at most one waker queue.
- *
- * A remarkable throughput boost can be reached by
- * unconditionally injecting the I/O of the waker
- * queue, every time a new bfq_dispatch_request
- * happens to be invoked while I/O is being plugged
- * for bfqq. In addition to boosting throughput, this
- * unblocks bfqq's I/O, thereby improving bandwidth
- * and latency for bfqq. Note that these same results
- * may be achieved with the general injection
- * mechanism, but less effectively. For details on
- * this aspect, see the comments on the choice of the
- * queue for injection in bfq_select_queue().
- *
- * Turning back to the detection of a waker queue, a
- * queue Q is deemed as a waker queue for bfqq if, for
- * two consecutive times, bfqq happens to become non
- * empty right after a request of Q has been
- * completed. In particular, on the first time, Q is
- * tentatively set as a candidate waker queue, while
- * on the second time, the flag
- * bfq_bfqq_has_waker(bfqq) is set to confirm that Q
- * is a waker queue for bfqq. These detection steps
- * are performed only if bfqq has a long think time,
- * so as to make it more likely that bfqq's I/O is
- * actually being blocked by a synchronization. This
- * last filter, plus the above two-times requirement,
- * make false positives less likely.
- *
- * NOTE
- *
- * The sooner a waker queue is detected, the sooner
- * throughput can be boosted by injecting I/O from the
- * waker queue. Fortunately, detection is likely to be
- * actually fast, for the following reasons. While
- * blocked by synchronization, bfqq has a long think
- * time. This implies that bfqq's inject limit is at
- * least equal to 1 (see the comments in
- * bfq_update_inject_limit()). So, thanks to
- * injection, the waker queue is likely to be served
- * during the very first I/O-plugging time interval
- * for bfqq. This triggers the first step of the
- * detection mechanism. Thanks again to injection, the
- * candidate waker queue is then likely to be
- * confirmed no later than during the next
- * I/O-plugging interval for bfqq.
- */
- if (bfqd->last_completed_rq_bfqq &&
- !bfq_bfqq_has_short_ttime(bfqq) &&
- ktime_get_ns() - bfqd->last_completion <
- 200 * NSEC_PER_USEC) {
- if (bfqd->last_completed_rq_bfqq != bfqq &&
- bfqd->last_completed_rq_bfqq !=
- bfqq->waker_bfqq) {
- /*
- * First synchronization detected with
- * a candidate waker queue, or with a
- * different candidate waker queue
- * from the current one.
- */
- bfqq->waker_bfqq = bfqd->last_completed_rq_bfqq;
-
- /*
- * If the waker queue disappears, then
- * bfqq->waker_bfqq must be reset. To
- * this goal, we maintain in each
- * waker queue a list, woken_list, of
- * all the queues that reference the
- * waker queue through their
- * waker_bfqq pointer. When the waker
- * queue exits, the waker_bfqq pointer
- * of all the queues in the woken_list
- * is reset.
- *
- * In addition, if bfqq is already in
- * the woken_list of a waker queue,
- * then, before being inserted into
- * the woken_list of a new waker
- * queue, bfqq must be removed from
- * the woken_list of the old waker
- * queue.
- */
- if (!hlist_unhashed(&bfqq->woken_list_node))
- hlist_del_init(&bfqq->woken_list_node);
- hlist_add_head(&bfqq->woken_list_node,
- &bfqd->last_completed_rq_bfqq->woken_list);
-
- bfq_clear_bfqq_has_waker(bfqq);
- } else if (bfqd->last_completed_rq_bfqq ==
- bfqq->waker_bfqq &&
- !bfq_bfqq_has_waker(bfqq)) {
- /*
- * synchronization with waker_bfqq
- * seen for the second time
- */
- bfq_mark_bfqq_has_waker(bfqq);
- }
- }
+ bfq_check_waker(bfqd, bfqq, now_ns);
/*
* Periodically reset inject limit, to make sure that
@@ -2047,6 +2089,9 @@ static void bfq_add_request(struct request *rq)
}
}
+ if (bfq_bfqq_sync(bfqq))
+ bfq_update_io_intensity(bfqq, now_ns);
+
elv_rb_add(&bfqq->sort_list, rq);
/*
@@ -2352,6 +2397,24 @@ static void bfq_requests_merged(struct request_queue *q, struct request *rq,
/* Must be called with bfqq != NULL */
static void bfq_bfqq_end_wr(struct bfq_queue *bfqq)
{
+ /*
+ * If bfqq has been enjoying interactive weight-raising, then
+ * reset soft_rt_next_start. We do it for the following
+ * reason. bfqq may have been conveying the I/O needed to load
+ * a soft real-time application. Such an application actually
+ * exhibits a soft real-time I/O pattern after it finishes
+ * loading, and finally starts doing its job. But, if bfqq has
+ * been receiving a lot of bandwidth so far (likely to happen
+ * on a fast device), then soft_rt_next_start now contains a
+ * high value that. So, without this reset, bfqq would be
+ * prevented from being possibly considered as soft_rt for a
+ * very long time.
+ */
+
+ if (bfqq->wr_cur_max_time !=
+ bfqq->bfqd->bfq_wr_rt_max_time)
+ bfqq->soft_rt_next_start = jiffies;
+
if (bfq_bfqq_busy(bfqq))
bfqq->bfqd->wr_busy_queues--;
bfqq->wr_coeff = 1;
@@ -2686,10 +2749,16 @@ static void bfq_bfqq_save_state(struct bfq_queue *bfqq)
if (!bic)
return;
+ bic->saved_last_serv_time_ns = bfqq->last_serv_time_ns;
+ bic->saved_inject_limit = bfqq->inject_limit;
+ bic->saved_decrease_time_jif = bfqq->decrease_time_jif;
+
bic->saved_weight = bfqq->entity.orig_weight;
bic->saved_ttime = bfqq->ttime;
bic->saved_has_short_ttime = bfq_bfqq_has_short_ttime(bfqq);
bic->saved_IO_bound = bfq_bfqq_IO_bound(bfqq);
+ bic->saved_io_start_time = bfqq->io_start_time;
+ bic->saved_tot_idle_time = bfqq->tot_idle_time;
bic->saved_in_large_burst = bfq_bfqq_in_large_burst(bfqq);
bic->was_in_burst_list = !hlist_unhashed(&bfqq->burst_list_node);
if (unlikely(bfq_bfqq_just_created(bfqq) &&
@@ -2712,6 +2781,7 @@ static void bfq_bfqq_save_state(struct bfq_queue *bfqq)
bic->saved_wr_coeff = bfqq->wr_coeff;
bic->saved_wr_start_at_switch_to_srt =
bfqq->wr_start_at_switch_to_srt;
+ bic->saved_service_from_wr = bfqq->service_from_wr;
bic->saved_last_wr_start_finish = bfqq->last_wr_start_finish;
bic->saved_wr_cur_max_time = bfqq->wr_cur_max_time;
}
@@ -2937,6 +3007,7 @@ static void __bfq_set_in_service_queue(struct bfq_data *bfqd,
}
bfqd->in_service_queue = bfqq;
+ bfqd->in_serv_last_pos = 0;
}
/*
@@ -3442,20 +3513,38 @@ static void bfq_dispatch_remove(struct request_queue *q, struct request *rq)
* order until all the requests already queued in the device have been
* served. The last sub-condition commented above somewhat mitigates
* this problem for weight-raised queues.
+ *
+ * However, as an additional mitigation for this problem, we preserve
+ * plugging for a special symmetric case that may suddenly turn into
+ * asymmetric: the case where only bfqq is busy. In this case, not
+ * expiring bfqq does not cause any harm to any other queues in terms
+ * of service guarantees. In contrast, it avoids the following unlucky
+ * sequence of events: (1) bfqq is expired, (2) a new queue with a
+ * lower weight than bfqq becomes busy (or more queues), (3) the new
+ * queue is served until a new request arrives for bfqq, (4) when bfqq
+ * is finally served, there are so many requests of the new queue in
+ * the drive that the pending requests for bfqq take a lot of time to
+ * be served. In particular, event (2) may case even already
+ * dispatched requests of bfqq to be delayed, inside the drive. So, to
+ * avoid this series of events, the scenario is preventively declared
+ * as asymmetric also if bfqq is the only busy queues
*/
static bool idling_needed_for_service_guarantees(struct bfq_data *bfqd,
struct bfq_queue *bfqq)
{
+ int tot_busy_queues = bfq_tot_busy_queues(bfqd);
+
/* No point in idling for bfqq if it won't get requests any longer */
if (unlikely(!bfqq_process_refs(bfqq)))
return false;
return (bfqq->wr_coeff > 1 &&
(bfqd->wr_busy_queues <
- bfq_tot_busy_queues(bfqd) ||
+ tot_busy_queues ||
bfqd->rq_in_driver >=
bfqq->dispatched + 4)) ||
- bfq_asymmetric_scenario(bfqd, bfqq);
+ bfq_asymmetric_scenario(bfqd, bfqq) ||
+ tot_busy_queues == 1;
}
static bool __bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq,
@@ -3939,10 +4028,6 @@ void bfq_bfqq_expire(struct bfq_data *bfqd,
bfq_bfqq_budget_left(bfqq) >= entity->budget / 3)))
bfq_bfqq_charge_time(bfqd, bfqq, delta);
- if (reason == BFQQE_TOO_IDLE &&
- entity->service <= 2 * entity->budget / 10)
- bfq_clear_bfqq_IO_bound(bfqq);
-
if (bfqd->low_latency && bfqq->wr_coeff == 1)
bfqq->last_wr_start_finish = jiffies;
@@ -3952,30 +4037,15 @@ void bfq_bfqq_expire(struct bfq_data *bfqd,
* If we get here, and there are no outstanding
* 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. 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.
+ * bfq_bfqq_softrt_next_start()). Therefore 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.
*/
- if (bfqq->dispatched == 0 &&
- bfqq->wr_coeff != bfqd->bfq_wr_coeff)
+ if (bfqq->dispatched == 0)
bfqq->soft_rt_next_start =
bfq_bfqq_softrt_next_start(bfqd, bfqq);
else if (bfqq->dispatched > 0) {
@@ -4497,9 +4567,9 @@ check_queue:
bfq_serv_to_charge(async_bfqq->next_rq, async_bfqq) <=
bfq_bfqq_budget_left(async_bfqq))
bfqq = bfqq->bic->bfqq[0];
- else if (bfq_bfqq_has_waker(bfqq) &&
+ else if (bfqq->waker_bfqq &&
bfq_bfqq_busy(bfqq->waker_bfqq) &&
- bfqq->next_rq &&
+ bfqq->waker_bfqq->next_rq &&
bfq_serv_to_charge(bfqq->waker_bfqq->next_rq,
bfqq->waker_bfqq) <=
bfq_bfqq_budget_left(bfqq->waker_bfqq)
@@ -4559,9 +4629,21 @@ static void bfq_update_wr_data(struct bfq_data *bfqd, struct bfq_queue *bfqq)
bfqq->wr_cur_max_time)) {
if (bfqq->wr_cur_max_time != bfqd->bfq_wr_rt_max_time ||
time_is_before_jiffies(bfqq->wr_start_at_switch_to_srt +
- bfq_wr_duration(bfqd)))
+ bfq_wr_duration(bfqd))) {
+ /*
+ * Either in interactive weight
+ * raising, or in soft_rt weight
+ * raising with the
+ * interactive-weight-raising period
+ * elapsed (so no switch back to
+ * interactive weight raising).
+ */
bfq_bfqq_end_wr(bfqq);
- else {
+ } else { /*
+ * soft_rt finishing while still in
+ * interactive period, switch back to
+ * interactive weight raising
+ */
switch_back_to_interactive_wr(bfqq, bfqd);
bfqq->entity.prio_changed = 1;
}
@@ -4640,9 +4722,6 @@ static bool bfq_has_work(struct blk_mq_hw_ctx *hctx)
{
struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
- if (!atomic_read(&hctx->elevator_queued))
- return false;
-
/*
* Avoiding lock: a race on bfqd->busy_queues should cause at
* most a call to dispatch for nothing
@@ -4892,7 +4971,6 @@ void bfq_put_queue(struct bfq_queue *bfqq)
hlist_for_each_entry_safe(item, n, &bfqq->woken_list,
woken_list_node) {
item->waker_bfqq = NULL;
- bfq_clear_bfqq_has_waker(item);
hlist_del_init(&item->woken_list_node);
}
@@ -5012,6 +5090,8 @@ bfq_set_next_ioprio_data(struct bfq_queue *bfqq, struct bfq_io_cq *bic)
}
bfqq->entity.new_weight = bfq_ioprio_to_weight(bfqq->new_ioprio);
+ bfq_log_bfqq(bfqd, bfqq, "new_ioprio %d new_weight %d",
+ bfqq->new_ioprio, bfqq->entity.new_weight);
bfqq->entity.prio_changed = 1;
}
@@ -5049,6 +5129,8 @@ static void bfq_check_ioprio_change(struct bfq_io_cq *bic, struct bio *bio)
static void bfq_init_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
struct bfq_io_cq *bic, pid_t pid, int is_sync)
{
+ u64 now_ns = ktime_get_ns();
+
RB_CLEAR_NODE(&bfqq->entity.rb_node);
INIT_LIST_HEAD(&bfqq->fifo);
INIT_HLIST_NODE(&bfqq->burst_list_node);
@@ -5076,7 +5158,9 @@ static void bfq_init_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
bfq_clear_bfqq_sync(bfqq);
/* set end request to minus infinity from now */
- bfqq->ttime.last_end_request = ktime_get_ns() + 1;
+ bfqq->ttime.last_end_request = now_ns + 1;
+
+ bfqq->io_start_time = now_ns;
bfq_mark_bfqq_IO_bound(bfqq);
@@ -5194,11 +5278,19 @@ static void bfq_update_io_thinktime(struct bfq_data *bfqd,
struct bfq_queue *bfqq)
{
struct bfq_ttime *ttime = &bfqq->ttime;
- u64 elapsed = ktime_get_ns() - bfqq->ttime.last_end_request;
+ u64 elapsed;
+ /*
+ * We are really interested in how long it takes for the queue to
+ * become busy when there is no outstanding IO for this queue. So
+ * ignore cases when the bfq queue has already IO queued.
+ */
+ if (bfqq->dispatched || bfq_bfqq_busy(bfqq))
+ return;
+ elapsed = ktime_get_ns() - bfqq->ttime.last_end_request;
elapsed = min_t(u64, elapsed, 2ULL * bfqd->bfq_slice_idle);
- ttime->ttime_samples = (7*bfqq->ttime.ttime_samples + 256) / 8;
+ ttime->ttime_samples = (7*ttime->ttime_samples + 256) / 8;
ttime->ttime_total = div_u64(7*ttime->ttime_total + 256*elapsed, 8);
ttime->ttime_mean = div64_ul(ttime->ttime_total + 128,
ttime->ttime_samples);
@@ -5213,8 +5305,26 @@ bfq_update_io_seektime(struct bfq_data *bfqd, struct bfq_queue *bfqq,
if (bfqq->wr_coeff > 1 &&
bfqq->wr_cur_max_time == bfqd->bfq_wr_rt_max_time &&
- BFQQ_TOTALLY_SEEKY(bfqq))
- bfq_bfqq_end_wr(bfqq);
+ BFQQ_TOTALLY_SEEKY(bfqq)) {
+ if (time_is_before_jiffies(bfqq->wr_start_at_switch_to_srt +
+ bfq_wr_duration(bfqd))) {
+ /*
+ * In soft_rt weight raising with the
+ * interactive-weight-raising period
+ * elapsed (so no switch back to
+ * interactive weight raising).
+ */
+ bfq_bfqq_end_wr(bfqq);
+ } else { /*
+ * stopping soft_rt weight raising
+ * while still in interactive period,
+ * switch back to interactive weight
+ * raising
+ */
+ switch_back_to_interactive_wr(bfqq, bfqd);
+ bfqq->entity.prio_changed = 1;
+ }
+ }
}
static void bfq_update_has_short_ttime(struct bfq_data *bfqd,
@@ -5238,12 +5348,13 @@ static void bfq_update_has_short_ttime(struct bfq_data *bfqd,
return;
/* Think time is infinite if no process is linked to
- * bfqq. Otherwise check average think time to
- * decide whether to mark as has_short_ttime
+ * bfqq. Otherwise check average think time to decide whether
+ * to mark as has_short_ttime. To this goal, compare average
+ * think time with half the I/O-plugging timeout.
*/
if (atomic_read(&bic->icq.ioc->active_ref) == 0 ||
(bfq_sample_valid(bfqq->ttime.ttime_samples) &&
- bfqq->ttime.ttime_mean > bfqd->bfq_slice_idle))
+ bfqq->ttime.ttime_mean > bfqd->bfq_slice_idle>>1))
has_short_ttime = false;
state_changed = has_short_ttime != bfq_bfqq_has_short_ttime(bfqq);
@@ -5557,7 +5668,6 @@ static void bfq_insert_requests(struct blk_mq_hw_ctx *hctx,
rq = list_first_entry(list, struct request, queuelist);
list_del_init(&rq->queuelist);
bfq_insert_request(hctx, rq, at_head);
- atomic_inc(&hctx->elevator_queued);
}
}
@@ -5925,7 +6035,6 @@ static void bfq_finish_requeue_request(struct request *rq)
bfq_completed_request(bfqq, bfqd);
bfq_finish_requeue_request_body(bfqq);
- atomic_dec(&rq->mq_hctx->elevator_queued);
spin_unlock_irqrestore(&bfqd->lock, flags);
} else {
@@ -6489,8 +6598,6 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
bfqd->bfq_slice_idle = bfq_slice_idle;
bfqd->bfq_timeout = bfq_timeout;
- bfqd->bfq_requests_within_timer = 120;
-
bfqd->bfq_large_burst_thresh = 8;
bfqd->bfq_burst_interval = msecs_to_jiffies(180);