// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Budget Fair Queueing (BFQ) I/O scheduler.
*
* Based on ideas and code from CFQ:
* Copyright (C) 2003 Jens Axboe <axboe@kernel.dk>
*
* Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it>
* Paolo Valente <paolo.valente@unimore.it>
*
* Copyright (C) 2010 Paolo Valente <paolo.valente@unimore.it>
* Arianna Avanzini <avanzini@google.com>
*
* Copyright (C) 2017 Paolo Valente <paolo.valente@linaro.org>
*
* BFQ is a proportional-share I/O scheduler, with some extra
* low-latency capabilities. BFQ also supports full hierarchical
* scheduling through cgroups. Next paragraphs provide an introduction
* on BFQ inner workings. Details on BFQ benefits, usage and
* limitations can be found in Documentation/block/bfq-iosched.rst.
*
* BFQ is a proportional-share storage-I/O scheduling algorithm based
* on the slice-by-slice service scheme of CFQ. But BFQ assigns
* budgets, measured in number of sectors, to processes instead of
* time slices. The device is not granted to the in-service process
* for a given time slice, but until it has exhausted its assigned
* budget. This change from the time to the service domain enables BFQ
* to distribute the device throughput among processes as desired,
* without any distortion due to throughput fluctuations, or to device
* internal queueing. BFQ uses an ad hoc internal scheduler, called
* B-WF2Q+, to schedule processes according to their budgets. More
* precisely, BFQ schedules queues associated with processes. Each
* process/queue is assigned a user-configurable weight, and B-WF2Q+
* guarantees that each queue receives a fraction of the throughput
* proportional to its weight. Thanks to the accurate policy of
* B-WF2Q+, BFQ can afford to assign high budgets to I/O-bound
* processes issuing sequential requests (to boost the throughput),
* and yet guarantee a low latency to interactive and soft real-time
* applications.
*
* In particular, to provide these low-latency guarantees, BFQ
* explicitly privileges the I/O of two classes of time-sensitive
* applications: interactive and soft real-time. In more detail, BFQ
* behaves this way if the low_latency parameter is set (default
* configuration). This feature enables BFQ to provide applications in
* these classes with a very low latency.
*
* To implement this feature, BFQ constantly tries to detect whether
* the I/O requests in a bfq_queue come from an interactive or a soft
* real-time application. For brevity, in these cases, the queue is
* said to be interactive or soft real-time. In both cases, BFQ
* privileges the service of the queue, over that of non-interactive
* and non-soft-real-time queues. This privileging is performed,
* mainly, by raising the weight of the queue. So, for brevity, we
* call just weight-raising periods the time periods during which a
* queue is privileged, because deemed interactive or soft real-time.
*
* The detection of soft real-time queues/applications is described in
* detail in the comments on the function
* bfq_bfqq_softrt_next_start. On the other hand, the detection of an
* interactive queue works as follows: a queue is deemed interactive
* if it is constantly non empty only for a limited time interval,
* after which it does become empty. The queue may be deemed
* interactive again (for a limited time), if it restarts being
* constantly non empty, provided that this happens only after the
* queue has remained empty for a given minimum idle time.
*
* By default, BFQ computes automatically the above maximum time
* interval, i.e., the time interval after which a constantly
* non-empty queue stops being deemed interactive. Since a queue is
* weight-raised while it is deemed interactive, this maximum time
* interval happens to coincide with the (maximum) duration of the
* weight-raising for interactive queues.
*
* Finally, BFQ also features additional heuristics for
* preserving both a low latency and a high throughput on NCQ-capable,
* rotational or flash-based devices, and to get the job done quickly
* for applications consisting in many I/O-bound processes.
*
* NOTE: if the main or only goal, with a given device, is to achieve
* the maximum-possible throughput at all times, then do switch off
* all low-latency heuristics for that device, by setting low_latency
* to 0.
*
* BFQ is described in [1], where also a reference to the initial,
* more theoretical paper on BFQ can be found. The interested reader
* can find in the latter paper full details on the main algorithm, as
* well as formulas of the guarantees and formal proofs of all the
* properties. With respect to the version of BFQ presented in these
* papers, this implementation adds a few more heuristics, such as the
* ones that guarantee a low latency to interactive and soft real-time
* applications, and a hierarchical extension based on H-WF2Q+.
*
* B-WF2Q+ is based on WF2Q+, which is described in [2], together with
* H-WF2Q+, while the augmented tree used here to implement B-WF2Q+
* with O(log N) complexity derives from the one introduced with EEVDF
* in [3].
*
* [1] P. Valente, A. Avanzini, "Evolution of the BFQ Storage I/O
* Scheduler", Proceedings of the First Workshop on Mobile System
* Technologies (MST-2015), May 2015.
* http://algogroup.unimore.it/people/paolo/disk_sched/mst-2015.pdf
*
* [2] Jon C.R. Bennett and H. Zhang, "Hierarchical Packet Fair Queueing
* Algorithms", IEEE/ACM Transactions on Networking, 5(5):675-689,
* Oct 1997.
*
* http://www.cs.cmu.edu/~hzhang/papers/TON-97-Oct.ps.gz
*
* [3] I. Stoica and H. Abdel-Wahab, "Earliest Eligible Virtual Deadline
* First: A Flexible and Accurate Mechanism for Proportional Share
* Resource Allocation", technical report.
*
* http://www.cs.berkeley.edu/~istoica/papers/eevdf-tr-95.pdf
*/
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/blkdev.h>
#include <linux/cgroup.h>
#include <linux/ktime.h>
#include <linux/rbtree.h>
#include <linux/ioprio.h>
#include <linux/sbitmap.h>
#include <linux/delay.h>
#include <linux/backing-dev.h>
#include <trace/events/block.h>
#include "elevator.h"
#include "blk.h"
#include "blk-mq.h"
#include "blk-mq-sched.h"
#include "bfq-iosched.h"
#include "blk-wbt.h"
#define BFQ_BFQQ_FNS(name) \
void bfq_mark_bfqq_
##name(
struct bfq_queue *bfqq) \
{ \
__set_bit(BFQQF_
##name, &(bfqq)->flags); \
} \
void bfq_clear_bfqq_
##name(
struct bfq_queue *bfqq) \
{ \
__clear_bit(BFQQF_
##name, &(bfqq)->flags); \
} \
int bfq_bfqq_
##name(
const struct bfq_queue *bfqq) \
{ \
return test_bit(BFQQF_
##name, &(bfqq)->flags); \
}
BFQ_BFQQ_FNS(just_created);
BFQ_BFQQ_FNS(busy);
BFQ_BFQQ_FNS(wait_request);
BFQ_BFQQ_FNS(non_blocking_wait_rq);
BFQ_BFQQ_FNS(fifo_expire);
BFQ_BFQQ_FNS(has_short_ttime);
BFQ_BFQQ_FNS(sync);
BFQ_BFQQ_FNS(IO_bound);
BFQ_BFQQ_FNS(in_large_burst);
BFQ_BFQQ_FNS(coop);
BFQ_BFQQ_FNS(split_coop);
BFQ_BFQQ_FNS(softrt_update);
#undef BFQ_BFQQ_FNS \
/* Expiration time of async (0) and sync (1) requests, in ns. */
static const u64 bfq_fifo_expire[2] = { NSEC_PER_SEC / 4, NSEC_PER_SEC / 8 };
/* Maximum backwards seek (magic number lifted from CFQ), in KiB. */
static const int bfq_back_max = 16 * 1024;
/* Penalty of a backwards seek, in number of sectors. */
static const int bfq_back_penalty = 2;
/* Idling period duration, in ns. */
static u64 bfq_slice_idle = NSEC_PER_SEC / 125;
/* Minimum number of assigned budgets for which stats are safe to compute. */
static const int bfq_stats_min_budgets = 194;
/* Default maximum budget values, in sectors and number of requests. */
static const int bfq_default_max_budget = 16 * 1024;
/*
* When a sync request is dispatched, the queue that contains that
* request, and all the ancestor entities of that queue, are charged
* with the number of sectors of the request. In contrast, if the
* request is async, then the queue and its ancestor entities are
* charged with the number of sectors of the request, multiplied by
* the factor below. This throttles the bandwidth for async I/O,
* w.r.t. to sync I/O, and it is done to counter the tendency of async
* writes to steal I/O throughput to reads.
*
* The current value of this parameter is the result of a tuning with
* several hardware and software configurations. We tried to find the
* lowest value for which writes do not cause noticeable problems to
* reads. In fact, the lower this parameter, the stabler I/O control,
* in the following respect. The lower this parameter is, the less
* the bandwidth enjoyed by a group decreases
* - when the group does writes, w.r.t. to when it does reads;
* - when other groups do reads, w.r.t. to when they do writes.
*/
static const int bfq_async_charge_factor = 3;
/* Default timeout values, in jiffies, approximating CFQ defaults. */
const int bfq_timeout = HZ / 8;
/*
* Time limit for merging (see comments in bfq_setup_cooperator). Set
* to the slowest value that, in our tests, proved to be effective in
* removing false positives, while not causing true positives to miss
* queue merging.
*
* As can be deduced from the low time limit below, queue merging, if
* successful, happens at the very beginning of the I/O of the involved
* cooperating processes, as a consequence of the arrival of the very
* first requests from each cooperator. After that, there is very
* little chance to find cooperators.
*/
static const unsigned long bfq_merge_time_limit = HZ/10;
static struct kmem_cache *bfq_pool;
/* Below this threshold (in ns), we consider thinktime immediate. */
#define BFQ_MIN_TT (2 * NSEC_PER_MSEC)
/* hw_tag detection: parallel requests threshold and min samples needed. */
#define BFQ_HW_QUEUE_THRESHOLD 3
#define BFQ_HW_QUEUE_SAMPLES 32
#define BFQQ_SEEK_THR (sector_t)(8 * 100)
#define BFQQ_SECT_THR_NONROT (sector_t)(2 * 32)
#define BFQ_RQ_SEEKY(bfqd, last_pos, rq) \
(get_sdist(last_pos, rq) > \
BFQQ_SEEK_THR && \
(!blk_queue_nonrot(bfqd->queue) || \
blk_rq_sectors(rq) < BFQQ_SECT_THR_NONROT))
#define BFQQ_CLOSE_THR (sector_t)(8 * 1024)
#define BFQQ_SEEKY(bfqq) (hweight32(bfqq->seek_history) > 19)
/*
* Sync random I/O is likely to be confused with soft real-time I/O,
* because it is characterized by limited throughput and apparently
* isochronous arrival pattern. To avoid false positives, queues
* containing only random (seeky) I/O are prevented from being tagged
* as soft real-time.
*/
#define BFQQ_TOTALLY_SEEKY(bfqq) (bfqq->seek_history == -1)
/* Min number of samples required to perform peak-rate update */
#define BFQ_RATE_MIN_SAMPLES 32
/* Min observation time interval required to perform a peak-rate update (ns) */
#define BFQ_RATE_MIN_INTERVAL (300*NSEC_PER_MSEC)
/* Target observation time interval for a peak-rate update (ns) */
#define BFQ_RATE_REF_INTERVAL NSEC_PER_SEC
/*
* Shift used for peak-rate fixed precision calculations.
* With
* - the current shift: 16 positions
* - the current type used to store rate: u32
* - the current unit of measure for rate: [sectors/usec], or, more precisely,
* [(sectors/usec) / 2^BFQ_RATE_SHIFT] to take into account the shift,
* the range of rates that can be stored is
* [1 / 2^BFQ_RATE_SHIFT, 2^(32 - BFQ_RATE_SHIFT)] sectors/usec =
* [1 / 2^16, 2^16] sectors/usec = [15e-6, 65536] sectors/usec =
* [15, 65G] sectors/sec
* Which, assuming a sector size of 512B, corresponds to a range of
* [7.5K, 33T] B/sec
*/
#define BFQ_RATE_SHIFT 16
/*
* When configured for computing the duration of the weight-raising
* for interactive queues automatically (see the comments at the
* beginning of this file), BFQ does it using the following formula:
* duration = (ref_rate / r) * ref_wr_duration,
* where r is the peak rate of the device, and ref_rate and
* ref_wr_duration are two reference parameters. In particular,
* ref_rate is the peak rate of the reference storage device (see
* below), and ref_wr_duration is about the maximum time needed, with
* BFQ and while reading two files in parallel, to load typical large
* applications on the reference device (see the comments on
* max_service_from_wr below, for more details on how ref_wr_duration
* is obtained). In practice, the slower/faster the device at hand
* is, the more/less it takes to load applications with respect to the
* reference device. Accordingly, the longer/shorter BFQ grants
* weight raising to interactive applications.
*
* BFQ uses two different reference pairs (ref_rate, ref_wr_duration),
* depending on whether the device is rotational or non-rotational.
*
* In the following definitions, ref_rate[0] and ref_wr_duration[0]
* are the reference values for a rotational device, whereas
* ref_rate[1] and ref_wr_duration[1] are the reference values for a
* non-rotational device. The reference rates are not the actual peak
* rates of the devices used as a reference, but slightly lower
* values. The reason for using slightly lower values is that the
* peak-rate estimator tends to yield slightly lower values than the
* actual peak rate (it can yield the actual peak rate only if there
* is only one process doing I/O, and the process does sequential
* I/O).
*
* The reference peak rates are measured in sectors/usec, left-shifted
* by BFQ_RATE_SHIFT.
*/
static int ref_rate[2] = {14000, 33000};
/*
* To improve readability, a conversion function is used to initialize
* the following array, which entails that the array can be
* initialized only in a function.
*/
static int ref_wr_duration[2];
/*
* BFQ uses the above-detailed, time-based weight-raising mechanism to
* privilege interactive tasks. This mechanism is vulnerable to the
* following false positives: I/O-bound applications that will go on
* doing I/O for much longer than the duration of weight
* raising. These applications have basically no benefit from being
* weight-raised at the beginning of their I/O. On the opposite end,
* while being weight-raised, these applications
* a) unjustly steal throughput to applications that may actually need
* low latency;
* b) make BFQ uselessly perform device idling; device idling results
* in loss of device throughput with most flash-based storage, and may
* increase latencies when used purposelessly.
*
* BFQ tries to reduce these problems, by adopting the following
* countermeasure. To introduce this countermeasure, we need first to
* finish explaining how the duration of weight-raising for
* interactive tasks is computed.
*
* For a bfq_queue deemed as interactive, the duration of weight
* raising is dynamically adjusted, as a function of the estimated
* peak rate of the device, so as to be equal to the time needed to
* execute the 'largest' interactive task we benchmarked so far. By
* largest task, we mean the task for which each involved process has
* to do more I/O than for any of the other tasks we benchmarked. This
* reference interactive task is the start-up of LibreOffice Writer,
* and in this task each process/bfq_queue needs to have at most ~110K
* sectors transferred.
*
* This last piece of information enables BFQ to reduce the actual
* duration of weight-raising for at least one class of I/O-bound
* applications: those doing sequential or quasi-sequential I/O. An
* example is file copy. In fact, once started, the main I/O-bound
* processes of these applications usually consume the above 110K
* sectors in much less time than the processes of an application that
* is starting, because these I/O-bound processes will greedily devote
* almost all their CPU cycles only to their target,
* throughput-friendly I/O operations. This is even more true if BFQ
* happens to be underestimating the device peak rate, and thus
* overestimating the duration of weight raising. But, according to
* our measurements, once transferred 110K sectors, these processes
* have no right to be weight-raised any longer.
*
* Basing on the last consideration, BFQ ends weight-raising for a
* bfq_queue if the latter happens to have received an amount of
* service at least equal to the following constant. The constant is
* set to slightly more than 110K, to have a minimum safety margin.
*
* This early ending of weight-raising reduces the amount of time
* during which interactive false positives cause the two problems
* described at the beginning of these comments.
*/
static const unsigned long max_service_from_wr = 120000;
/*
* Maximum time between the creation of two queues, for stable merge
* to be activated (in ms)
*/
static const unsigned long bfq_activation_stable_merging = 600;
/*
* Minimum time to be waited before evaluating delayed stable merge (in ms)
*/
static const unsigned long bfq_late_stable_merging = 600;
#define RQ_BIC(rq) ((
struct bfq_io_cq *)((rq)->elv.priv[0]))
#define RQ_BFQQ(rq) ((rq)->elv.priv[1])
struct bfq_queue *bic_to_bfqq(
struct bfq_io_cq *bic,
bool is_sync,
unsigned int actuator_idx)
{
if (is_sync)
return bic->bfqq[1][actuator_idx];
return bic->bfqq[0][actuator_idx];
}
static void bfq_put_stable_ref(
struct bfq_queue *bfqq);
void bic_set_bfqq(
struct bfq_io_cq *bic,
struct bfq_queue *bfqq,
bool is_sync,
unsigned int actuator_idx)
{
struct bfq_queue *old_bfqq = bic->bfqq[is_sync][actuator_idx];
/*
* If bfqq != NULL, then a non-stable queue merge between
* bic->bfqq and bfqq is happening here. This causes troubles
* in the following case: bic->bfqq has also been scheduled
* for a possible stable merge with bic->stable_merge_bfqq,
* and bic->stable_merge_bfqq == bfqq happens to
* hold. Troubles occur because bfqq may then undergo a split,
* thereby becoming eligible for a stable merge. Yet, if
* bic->stable_merge_bfqq points exactly to bfqq, then bfqq
* would be stably merged with itself. To avoid this anomaly,
* we cancel the stable merge if
* bic->stable_merge_bfqq == bfqq.
*/
struct bfq_iocq_bfqq_data *bfqq_data = &bic->bfqq_data[actuator_idx];
/* Clear bic pointer if bfqq is detached from this bic */
if (old_bfqq && old_bfqq->bic == bic)
old_bfqq->bic = NULL;
if (is_sync)
bic->bfqq[1][actuator_idx] = bfqq;
else
bic->bfqq[0][actuator_idx] = bfqq;
if (bfqq && bfqq_data->stable_merge_bfqq == bfqq) {
/*
* Actually, these same instructions are executed also
* in bfq_setup_cooperator, in case of abort or actual
* execution of a stable merge. We could avoid
* repeating these instructions there too, but if we
* did so, we would nest even more complexity in this
* function.
*/
bfq_put_stable_ref(bfqq_data->stable_merge_bfqq);
bfqq_data->stable_merge_bfqq = NULL;
}
}
struct bfq_data *bic_to_bfqd(
struct bfq_io_cq *bic)
{
return bic->icq.q->elevator->elevator_data;
}
/**
* icq_to_bic - convert iocontext queue structure to bfq_io_cq.
* @icq: the iocontext queue.
*/
static struct bfq_io_cq *icq_to_bic(
struct io_cq *icq)
{
/* bic->icq is the first member, %NULL will convert to %NULL */
return container_of(icq,
struct bfq_io_cq, icq);
}
/**
* bfq_bic_lookup - search into @ioc a bic associated to @bfqd.
* @q: the request queue.
*/
static struct bfq_io_cq *bfq_bic_lookup(
struct request_queue *q)
{
if (!current->io_context)
return NULL;
return icq_to_bic(ioc_lookup_icq(q));
}
/*
* Scheduler run of queue, if there are requests pending and no one in the
* driver that will restart queueing.
*/
void bfq_schedule_dispatch(
struct bfq_data *bfqd)
{
lockdep_assert_held(&bfqd->lock);
if (bfqd->queued != 0) {
bfq_log(bfqd,
"schedule dispatch");
blk_mq_run_hw_queues(bfqd->queue,
true);
}
}
#define bfq_class_idle(bfqq) ((bfqq)->ioprio_class == IOPRIO_CLASS_IDLE)
#define bfq_sample_valid(samples) ((samples) > 80)
/*
* Lifted from AS - choose which of rq1 and rq2 that is best served now.
* We choose the request that is closer to the head right now. Distance
* behind the head is penalized and only allowed to a certain extent.
*/
static struct request *bfq_choose_req(
struct bfq_data *bfqd,
struct request *rq1,
struct request *rq2,
sector_t last)
{
sector_t s1, s2, d1 = 0, d2 = 0;
unsigned long back_max;
#define BFQ_RQ1_WRAP 0x01
/* request 1 wraps */
#define BFQ_RQ2_WRAP 0x02
/* request 2 wraps */
unsigned int wrap = 0;
/* bit mask: requests behind the disk head? */
if (!rq1 || rq1 == rq2)
return rq2;
if (!rq2)
return rq1;
if (rq_is_sync(rq1) && !rq_is_sync(rq2))
return rq1;
else if (rq_is_sync(rq2) && !rq_is_sync(rq1))
return rq2;
if ((rq1->cmd_flags & REQ_META) && !(rq2->cmd_flags & REQ_META))
return rq1;
else if ((rq2->cmd_flags & REQ_META) && !(rq1->cmd_flags & REQ_META))
return rq2;
s1 = blk_rq_pos(rq1);
s2 = blk_rq_pos(rq2);
/*
* By definition, 1KiB is 2 sectors.
*/
back_max = bfqd->bfq_back_max * 2;
/*
* Strict one way elevator _except_ in the case where we allow
* short backward seeks which are biased as twice the cost of a
* similar forward seek.
*/
if (s1 >= last)
d1 = s1 - last;
else if (s1 + back_max >= last)
d1 = (last - s1) * bfqd->bfq_back_penalty;
else
wrap |= BFQ_RQ1_WRAP;
if (s2 >= last)
d2 = s2 - last;
else if (s2 + back_max >= last)
d2 = (last - s2) * bfqd->bfq_back_penalty;
else
wrap |= BFQ_RQ2_WRAP;
/* Found required data */
/*
* By doing switch() on the bit mask "wrap" we avoid having to
* check two variables for all permutations: --> faster!
*/
switch (wrap) {
case 0:
/* common case for CFQ: rq1 and rq2 not wrapped */
if (d1 < d2)
return rq1;
else if (d2 < d1)
return rq2;
if (s1 >= s2)
return rq1;
else
return rq2;
case BFQ_RQ2_WRAP:
return rq1;
case BFQ_RQ1_WRAP:
return rq2;
case BFQ_RQ1_WRAP|BFQ_RQ2_WRAP:
/* both rqs wrapped */
default:
/*
* Since both rqs are wrapped,
* start with the one that's further behind head
* (--> only *one* back seek required),
* since back seek takes more time than forward.
*/
if (s1 <= s2)
return rq1;
else
return rq2;
}
}
#define BFQ_LIMIT_INLINE_DEPTH 16
#ifdef CONFIG_BFQ_GROUP_IOSCHED
static bool bfqq_request_over_limit(
struct bfq_data *bfqd,
struct bfq_io_cq *bic, blk_opf_t opf,
unsigned int act_idx,
int limit)
{
struct bfq_entity *inline_entities[BFQ_LIMIT_INLINE_DEPTH];
struct bfq_entity **entities = inline_entities;
int alloc_depth = BFQ_LIMIT_INLINE_DEPTH;
struct bfq_sched_data *sched_data;
struct bfq_entity *entity;
struct bfq_queue *bfqq;
unsigned long wsum;
bool ret =
false;
int depth;
int level;
retry:
spin_lock_irq(&bfqd->lock);
bfqq = bic_to_bfqq(bic, op_is_sync(opf), act_idx);
if (!bfqq)
goto out;
entity = &bfqq->entity;
if (!entity->on_st_or_in_serv)
goto out;
/* +1 for bfqq entity, root cgroup not included */
depth = bfqg_to_blkg(bfqq_group(bfqq))->blkcg->css.cgroup->level + 1;
if (depth > alloc_depth) {
spin_unlock_irq(&bfqd->lock);
if (entities != inline_entities)
kfree(entities);
entities = kmalloc_array(depth,
sizeof(*entities), GFP_NOIO);
if (!entities)
return false;
alloc_depth = depth;
goto retry;
}
sched_data = entity->sched_data;
/* Gather our ancestors as we need to traverse them in reverse order */
level = 0;
for_each_entity(entity) {
/*
* If at some level entity is not even active, allow request
* queueing so that BFQ knows there's work to do and activate
* entities.
*/
if (!entity->on_st_or_in_serv)
goto out;
/* Uh, more parents than cgroup subsystem thinks? */
if (WARN_ON_ONCE(level >= depth))
break;
entities[level++] = entity;
}
WARN_ON_ONCE(level != depth);
for (level--; level >= 0; level--) {
entity = entities[level];
if (level > 0) {
wsum = bfq_entity_service_tree(entity)->wsum;
}
else {
int i;
/*
* For bfqq itself we take into account service trees
* of all higher priority classes and multiply their
* weights so that low prio queue from higher class
* gets more requests than high prio queue from lower
* class.
*/
wsum = 0;
for (i = 0; i <= bfqq->ioprio_class - 1; i++) {
wsum = wsum * IOPRIO_BE_NR +
sched_data->service_tree[i].wsum;
}
}
if (!wsum)
continue;
limit = DIV_ROUND_CLOSEST(limit * entity->weight, wsum);
if (entity->allocated >= limit) {
bfq_log_bfqq(bfqq->bfqd, bfqq,
"too many requests: allocated %d limit %d level %d",
entity->allocated, limit, level);
ret =
true;
break;
}
}
out:
spin_unlock_irq(&bfqd->lock);
if (entities != inline_entities)
kfree(entities);
return ret;
}
#else
static bool bfqq_request_over_limit(
struct bfq_data *bfqd,
struct bfq_io_cq *bic, blk_opf_t opf,
unsigned int act_idx,
int limit)
{
return false;
}
#endif
/*
* Async I/O can easily starve sync I/O (both sync reads and sync
* writes), by consuming all tags. Similarly, storms of sync writes,
* such as those that sync(2) may trigger, can starve sync reads.
* Limit depths of async I/O and sync writes so as to counter both
* problems.
*
* Also if a bfq queue or its parent cgroup consume more tags than would be
* appropriate for their weight, we trim the available tag depth to 1. This
* avoids a situation where one cgroup can starve another cgroup from tags and
* thus block service differentiation among cgroups. Note that because the
* queue / cgroup already has many requests allocated and queued, this does not
* significantly affect service guarantees coming from the BFQ scheduling
* algorithm.
*/
static void bfq_limit_depth(blk_opf_t opf,
struct blk_mq_alloc_data *data)
{
struct bfq_data *bfqd = data->q->elevator->elevator_data;
struct bfq_io_cq *bic = bfq_bic_lookup(data->q);
unsigned int limit, act_idx;
/* Sync reads have full depth available */
if (op_is_sync(opf) && !op_is_write(opf))
limit = data->q->nr_requests;
else
limit = bfqd->async_depths[!!bfqd->wr_busy_queues][op_is_sync(opf)];
for (act_idx = 0; bic && act_idx < bfqd->num_actuators; act_idx++) {
/* Fast path to check if bfqq is already allocated. */
if (!bic_to_bfqq(bic, op_is_sync(opf), act_idx))
continue;
/*
* Does queue (or any parent entity) exceed number of
* requests that should be available to it? Heavily
* limit depth so that it cannot consume more
* available requests and thus starve other entities.
*/
if (bfqq_request_over_limit(bfqd, bic, opf, act_idx, limit)) {
limit = 1;
break;
}
}
bfq_log(bfqd,
"[%s] wr_busy %d sync %d depth %u",
__func__, bfqd->wr_busy_queues, op_is_sync(opf), limit);
if (limit < data->q->nr_requests)
data->shallow_depth = limit;
}
static struct bfq_queue *
bfq_rq_pos_tree_lookup(
struct bfq_data *bfqd,
struct rb_root *root,
sector_t sector,
struct rb_node **ret_parent,
struct rb_node ***rb_link)
{
struct rb_node **p, *parent;
struct bfq_queue *bfqq = NULL;
parent = NULL;
p = &root->rb_node;
while (*p) {
struct rb_node **n;
parent = *p;
bfqq = rb_entry(parent,
struct bfq_queue, pos_node);
/*
* Sort strictly based on sector. Smallest to the left,
* largest to the right.
*/
if (sector > blk_rq_pos(bfqq->next_rq))
n = &(*p)->rb_right;
else if (sector < blk_rq_pos(bfqq->next_rq))
n = &(*p)->rb_left;
else
break;
p = n;
bfqq = NULL;
}
*ret_parent = parent;
if (rb_link)
*rb_link = p;
bfq_log(bfqd,
"rq_pos_tree_lookup %llu: returning %d",
(
unsigned long long)sector,
bfqq ? bfqq->pid : 0);
return bfqq;
}
static bool bfq_too_late_for_merging(
struct bfq_queue *bfqq)
{
return bfqq->service_from_backlogged > 0 &&
time_is_before_jiffies(bfqq->first_IO_time +
bfq_merge_time_limit);
}
/*
* The following function is not marked as __cold because it is
* actually cold, but for the same performance goal described in the
* comments on the likely() at the beginning of
* bfq_setup_cooperator(). Unexpectedly, to reach an even lower
* execution time for the case where this function is not invoked, we
* had to add an unlikely() in each involved if().
*/
void __cold
bfq_pos_tree_add_move(
struct bfq_data *bfqd,
struct bfq_queue *bfqq)
{
struct rb_node **p, *parent;
struct bfq_queue *__bfqq;
if (bfqq->pos_root) {
rb_erase(&bfqq->pos_node, bfqq->pos_root);
bfqq->pos_root = NULL;
}
/* oom_bfqq does not participate in queue merging */
if (bfqq == &bfqd->oom_bfqq)
return;
/*
* bfqq cannot be merged any longer (see comments in
* bfq_setup_cooperator): no point in adding bfqq into the
* position tree.
*/
if (bfq_too_late_for_merging(bfqq))
return;
if (bfq_class_idle(bfqq))
return;
if (!bfqq->next_rq)
return;
bfqq->pos_root = &bfqq_group(bfqq)->rq_pos_tree;
__bfqq = bfq_rq_pos_tree_lookup(bfqd, bfqq->pos_root,
blk_rq_pos(bfqq->next_rq), &parent, &p);
if (!__bfqq) {
rb_link_node(&bfqq->pos_node, parent, p);
rb_insert_color(&bfqq->pos_node, bfqq->pos_root);
}
else
bfqq->pos_root = NULL;
}
/*
* The following function returns false either if every active queue
* must receive the same share of the throughput (symmetric scenario),
* or, as a special case, if bfqq must receive a share of the
* throughput lower than or equal to the share that every other active
* queue must receive. If bfqq does sync I/O, then these are the only
* two cases where bfqq happens to be guaranteed its share of the
* throughput even if I/O dispatching is not plugged when bfqq remains
* temporarily empty (for more details, see the comments in the
* function bfq_better_to_idle()). For this reason, the return value
* of this function is used to check whether I/O-dispatch plugging can
* be avoided.
*
* The above first case (symmetric scenario) occurs when:
* 1) all active queues 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 three sub-conditions, for which it is
* much easier to maintain the needed state:
* 1) all active queues have the same weight,
* 2) all active queues belong to the same I/O-priority class,
* 3) there is at most one active group.
* 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_asymmetric_scenario(
struct bfq_data *bfqd,
struct bfq_queue *bfqq)
{
bool smallest_weight = bfqq &&
bfqq->weight_counter &&
bfqq->weight_counter ==
container_of(
rb_first_cached(&bfqd->queue_weights_tree),
struct bfq_weight_counter,
weights_node);
/*
* For queue weights to differ, queue_weights_tree must contain
* at least two nodes.
*/
bool varied_queue_weights = !smallest_weight &&
!RB_EMPTY_ROOT(&bfqd->queue_weights_tree.rb_root) &&
(bfqd->queue_weights_tree.rb_root.rb_node->rb_left ||
bfqd->queue_weights_tree.rb_root.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]);
return varied_queue_weights || multiple_classes_busy
#ifdef CONFIG_BFQ_GROUP_IOSCHED
|| bfqd->num_groups_with_pending_reqs > 1
#endif
;
}
/*
* If the weight-counter tree passed as input contains no counter for
* the weight of the input queue, then add that counter; otherwise just
* increment the existing counter.
*
* Note that weight-counter trees contain few nodes in mostly symmetric
* scenarios. For example, if all queues have the same weight, then the
* weight-counter tree for the queues may contain at most one node.
* This holds even if low_latency is on, because weight-raised queues
* are not inserted in the tree.
* In most scenarios, the rate at which nodes are created/destroyed
* should be low too.
*/
void bfq_weights_tree_add(
struct bfq_queue *bfqq)
{
struct rb_root_cached *root = &bfqq->bfqd->queue_weights_tree;
struct bfq_entity *entity = &bfqq->entity;
struct rb_node **
new = &(root->rb_root.rb_node), *parent = NULL;
bool leftmost =
true;
/*
* Do not insert if the queue is already associated with a
* counter, which happens if:
* 1) a request arrival has caused the queue to become both
* non-weight-raised, and hence change its weight, and
* backlogged; in this respect, each of the two events
* causes an invocation of this function,
* 2) this is the invocation of this function caused by the
* second event. This second invocation is actually useless,
* and we handle this fact by exiting immediately. More
* efficient or clearer solutions might possibly be adopted.
*/
if (bfqq->weight_counter)
return;
while (*
new) {
struct bfq_weight_counter *__counter = container_of(*
new,
struct bfq_weight_counter,
weights_node);
parent = *
new;
if (entity->weight == __counter->weight) {
bfqq->weight_counter = __counter;
goto inc_counter;
}
if (entity->weight < __counter->weight)
new = &((*
new)->rb_left);
else {
new = &((*
new)->rb_right);
leftmost =
false;
}
}
bfqq->weight_counter = kzalloc(
sizeof(
struct bfq_weight_counter),
GFP_ATOMIC);
/*
* In the unlucky event of an allocation failure, we just
* exit. This will cause the weight of queue to not be
* considered in bfq_asymmetric_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;
bfqq->weight_counter->weight = entity->weight;
rb_link_node(&bfqq->weight_counter->weights_node, parent,
new);
rb_insert_color_cached(&bfqq->weight_counter->weights_node, root,
leftmost);
inc_counter:
bfqq->weight_counter->num_active++;
bfqq->ref++;
}
/*
* Decrement the weight counter associated with the queue, and, if the
* counter reaches 0, remove the counter from the tree.
* See the comments to the function bfq_weights_tree_add() for considerations
* about overhead.
*/
void bfq_weights_tree_remove(
struct bfq_queue *bfqq)
{
struct rb_root_cached *root;
if (!bfqq->weight_counter)
return;
root = &bfqq->bfqd->queue_weights_tree;
bfqq->weight_counter->num_active--;
if (bfqq->weight_counter->num_active > 0)
goto reset_entity_pointer;
rb_erase_cached(&bfqq->weight_counter->weights_node, root);
kfree(bfqq->weight_counter);
reset_entity_pointer:
bfqq->weight_counter = NULL;
bfq_put_queue(bfqq);
}
/*
* Return expired entry, or NULL to just start from scratch in rbtree.
*/
static struct request *bfq_check_fifo(
struct bfq_queue *bfqq,
struct request *last)
{
struct request *rq;
if (bfq_bfqq_fifo_expire(bfqq))
return NULL;
bfq_mark_bfqq_fifo_expire(bfqq);
rq = rq_entry_fifo(bfqq->fifo.next);
if (rq == last || blk_time_get_ns() < rq->fifo_time)
return NULL;
bfq_log_bfqq(bfqq->bfqd, bfqq,
"check_fifo: returned %p", rq);
return rq;
}
static struct request *bfq_find_next_rq(
struct bfq_data *bfqd,
struct bfq_queue *bfqq,
struct request *last)
{
struct rb_node *rbnext = rb_next(&last->rb_node);
struct rb_node *rbprev = rb_prev(&last->rb_node);
struct request *next, *prev = NULL;
/* Follow expired path, else get first next available. */
next = bfq_check_fifo(bfqq, last);
if (next)
return next;
if (rbprev)
prev = rb_entry_rq(rbprev);
if (rbnext)
next = rb_entry_rq(rbnext);
else {
rbnext = rb_first(&bfqq->sort_list);
if (rbnext && rbnext != &last->rb_node)
next = rb_entry_rq(rbnext);
}
return bfq_choose_req(bfqd, next, prev, blk_rq_pos(last));
}
/* see the definition of bfq_async_charge_factor for details */
static unsigned long bfq_serv_to_charge(
struct request *rq,
struct bfq_queue *bfqq)
{
if (bfq_bfqq_sync(bfqq) || bfqq->wr_coeff > 1 ||
bfq_asymmetric_scenario(bfqq->bfqd, bfqq))
return blk_rq_sectors(rq);
return blk_rq_sectors(rq) * bfq_async_charge_factor;
}
/**
* bfq_updated_next_req - update the queue after a new next_rq selection.
* @bfqd: the device data the queue belongs to.
* @bfqq: the queue to update.
*
* If the first request of a queue changes we make sure that the queue
* has enough budget to serve at least its first request (if the
* request has grown). We do this because if the queue has not enough
* budget for its first request, it has to go through two dispatch
* rounds to actually get it dispatched.
*/
static void bfq_updated_next_req(
struct bfq_data *bfqd,
struct bfq_queue *bfqq)
{
struct bfq_entity *entity = &bfqq->entity;
struct request *next_rq = bfqq->next_rq;
unsigned long new_budget;
if (!next_rq)
return;
if (bfqq == bfqd->in_service_queue)
/*
* In order not to break guarantees, budgets cannot be
* changed after an entity has been selected.
*/
return;
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",
new_budget);
bfq_requeue_bfqq(bfqd, bfqq,
false);
}
}
static unsigned int bfq_wr_duration(
struct bfq_data *bfqd)
{
u64 dur;
dur = bfqd->rate_dur_prod;
do_div(dur, bfqd->peak_rate);
/*
* Limit duration between 3 and 25 seconds. The upper limit
* has been conservatively set after the following worst case:
* on a QEMU/KVM virtual machine
* - running in a slow PC
* - with a virtual disk stacked on a slow low-end 5400rpm HDD
* - serving a heavy I/O workload, such as the sequential reading
* of several files
* mplayer took 23 seconds to start, if constantly weight-raised.
*
* As for higher values than that accommodating the above bad
* scenario, tests show that higher values would often yield
* the opposite of the desired result, i.e., would worsen
* responsiveness by allowing non-interactive applications to
* preserve weight raising for too long.
*
* On the other end, lower values than 3 seconds make it
* difficult for most interactive tasks to complete their jobs
* before weight-raising finishes.
*/
return clamp_val(dur, msecs_to_jiffies(3000), msecs_to_jiffies(25000));
}
/* switch back from soft real-time to interactive weight raising */
static void switch_back_to_interactive_wr(
struct bfq_queue *bfqq,
struct bfq_data *bfqd)
{
bfqq->wr_coeff = bfqd->bfq_wr_coeff;
bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
bfqq->last_wr_start_finish = bfqq->wr_start_at_switch_to_srt;
}
static void
bfq_bfqq_resume_state(
struct bfq_queue *bfqq,
struct bfq_data *bfqd,
struct bfq_io_cq *bic,
bool bfq_already_existing)
{
unsigned int old_wr_coeff = 1;
bool busy = bfq_already_existing && bfq_bfqq_busy(bfqq);
unsigned int a_idx = bfqq->actuator_idx;
struct bfq_iocq_bfqq_data *bfqq_data = &bic->bfqq_data[a_idx];
if (bfqq_data->saved_has_short_ttime)
bfq_mark_bfqq_has_short_ttime(bfqq);
else
bfq_clear_bfqq_has_short_ttime(bfqq);
if (bfqq_data->saved_IO_bound)
bfq_mark_bfqq_IO_bound(bfqq);
else
bfq_clear_bfqq_IO_bound(bfqq);
bfqq->last_serv_time_ns = bfqq_data->saved_last_serv_time_ns;
bfqq->inject_limit = bfqq_data->saved_inject_limit;
bfqq->decrease_time_jif = bfqq_data->saved_decrease_time_jif;
bfqq->entity.new_weight = bfqq_data->saved_weight;
bfqq->ttime = bfqq_data->saved_ttime;
bfqq->io_start_time = bfqq_data->saved_io_start_time;
bfqq->tot_idle_time = bfqq_data->saved_tot_idle_time;
/*
* Restore weight coefficient only if low_latency is on
*/
if (bfqd->low_latency) {
old_wr_coeff = bfqq->wr_coeff;
bfqq->wr_coeff = bfqq_data->saved_wr_coeff;
}
bfqq->service_from_wr = bfqq_data->saved_service_from_wr;
bfqq->wr_start_at_switch_to_srt =
bfqq_data->saved_wr_start_at_switch_to_srt;
bfqq->last_wr_start_finish = bfqq_data->saved_last_wr_start_finish;
bfqq->wr_cur_max_time = bfqq_data->saved_wr_cur_max_time;
if (bfqq->wr_coeff > 1 && (bfq_bfqq_in_large_burst(bfqq) ||
time_is_before_jiffies(bfqq->last_wr_start_finish +
bfqq->wr_cur_max_time))) {
if (bfqq->wr_cur_max_time == bfqd->bfq_wr_rt_max_time &&
!bfq_bfqq_in_large_burst(bfqq) &&
time_is_after_eq_jiffies(bfqq->wr_start_at_switch_to_srt +
bfq_wr_duration(bfqd))) {
switch_back_to_interactive_wr(bfqq, bfqd);
}
else {
bfqq->wr_coeff = 1;
bfq_log_bfqq(bfqq->bfqd, bfqq,
"resume state: switching off wr");
}
}
/* make sure weight will be updated, however we got here */
bfqq->entity.prio_changed = 1;
if (likely(!busy))
return;
if (old_wr_coeff == 1 && bfqq->wr_coeff > 1)
bfqd->wr_busy_queues++;
else if (old_wr_coeff > 1 && bfqq->wr_coeff == 1)
bfqd->wr_busy_queues--;
}
static int bfqq_process_refs(
struct bfq_queue *bfqq)
{
return bfqq->ref - bfqq->entity.allocated -
bfqq->entity.on_st_or_in_serv -
(bfqq->weight_counter != NULL) - bfqq->stable_ref;
}
/* Empty burst list and add just bfqq (see comments on bfq_handle_burst) */
static void bfq_reset_burst_list(
struct bfq_data *bfqd,
struct bfq_queue *bfqq)
{
struct bfq_queue *item;
struct hlist_node *n;
hlist_for_each_entry_safe(item, n, &bfqd->burst_list, burst_list_node)
hlist_del_init(&item->burst_list_node);
/*
* Start the creation of a new burst list only if there is no
* active queue. See comments on the conditional invocation of
* bfq_handle_burst().
*/
if (bfq_tot_busy_queues(bfqd) == 0) {
hlist_add_head(&bfqq->burst_list_node, &bfqd->burst_list);
bfqd->burst_size = 1;
}
else
bfqd->burst_size = 0;
bfqd->burst_parent_entity = bfqq->entity.parent;
}
/* Add bfqq to the list of queues in current burst (see bfq_handle_burst) */
static void bfq_add_to_burst(
struct bfq_data *bfqd,
struct bfq_queue *bfqq)
{
/* Increment burst size to take into account also bfqq */
bfqd->burst_size++;
if (bfqd->burst_size == bfqd->bfq_large_burst_thresh) {
struct bfq_queue *pos, *bfqq_item;
struct hlist_node *n;
/*
* Enough queues have been activated shortly after each
* other to consider this burst as large.
*/
bfqd->large_burst =
true;
/*
* We can now mark all queues in the burst list as
* belonging to a large burst.
*/
hlist_for_each_entry(bfqq_item, &bfqd->burst_list,
burst_list_node)
bfq_mark_bfqq_in_large_burst(bfqq_item);
bfq_mark_bfqq_in_large_burst(bfqq);
/*
* From now on, and until the current burst finishes, any
* new queue being activated shortly after the last queue
* was inserted in the burst can be immediately marked as
* belonging to a large burst. So the burst list is not
* needed any more. Remove it.
*/
hlist_for_each_entry_safe(pos, n, &bfqd->burst_list,
burst_list_node)
hlist_del_init(&pos->burst_list_node);
}
else /*
* Burst not yet large: add bfqq to the burst list. Do
* not increment the ref counter for bfqq, because bfqq
* is removed from the burst list before freeing bfqq
* in put_queue.
*/
hlist_add_head(&bfqq->burst_list_node, &bfqd->burst_list);
}
/*
* If many queues belonging to the same group happen to be created
* shortly after each other, then the processes associated with these
* queues have typically a common goal. In particular, bursts of queue
* creations are usually caused by services or applications that spawn
* many parallel threads/processes. Examples are systemd during boot,
* or git grep. To help these processes get their job done as soon as
* possible, it is usually better to not grant either weight-raising
* or device idling to their queues, unless these queues must be
* protected from the I/O flowing through other active queues.
*
* In this comment we describe, firstly, the reasons why this fact
* holds, and, secondly, the next function, which implements the main
* steps needed to properly mark these queues so that they can then be
* treated in a different way.
*
* The above services or applications benefit mostly from a high
* throughput: the quicker the requests of the activated queues are
* cumulatively served, the sooner the target job of these queues gets
* completed. As a consequence, weight-raising any of these queues,
* which also implies idling the device for it, is almost always
* counterproductive, unless there are other active queues to isolate
* these new queues from. If there no other active queues, then
* weight-raising these new queues just lowers throughput in most
* cases.
*
* On the other hand, a burst of queue creations may be caused also by
* the start of an application that does not consist of a lot of
* parallel I/O-bound threads. In fact, with a complex application,
* several short processes may need to be executed to start-up the
* application. In this respect, to start an application as quickly as
* possible, the best thing to do is in any case to privilege the I/O
* related to the application with respect to all other
* I/O. Therefore, the best strategy to start as quickly as possible
* an application that causes a burst of queue creations is to
* weight-raise all the queues created during the burst. This is the
* exact opposite of the best strategy for the other type of bursts.
*
* In the end, to take the best action for each of the two cases, the
* two types of bursts need to be distinguished. Fortunately, this
* seems relatively easy, by looking at the sizes of the bursts. In
* particular, we found a threshold such that only bursts with a
* larger size than that threshold are apparently caused by
* services or commands such as systemd or git grep. For brevity,
* hereafter we call just 'large' these bursts. BFQ *does not*
* weight-raise queues whose creation occurs in a large burst. In
* addition, for each of these queues BFQ performs or does not perform
* idling depending on which choice boosts the throughput more. The
* exact choice depends on the device and request pattern at
* hand.
*
* Unfortunately, false positives may occur while an interactive task
* is starting (e.g., an application is being started). The
* consequence is that the queues associated with the task do not
* enjoy weight raising as expected. Fortunately these false positives
* are very rare. They typically occur if some service happens to
* start doing I/O exactly when the interactive task starts.
*
* Turning back to the next function, it is invoked only if there are
* no active queues (apart from active queues that would belong to the
* same, possible burst bfqq would belong to), and it implements all
* the steps needed to detect the occurrence of a large burst and to
* properly mark all the queues belonging to it (so that they can then
* be treated in a different way). This goal is achieved by
* maintaining a "burst list" that holds, temporarily, the queues that
* belong to the burst in progress. The list is then used to mark
* these queues as belonging to a large burst if the burst does become
* large. The main steps are the following.
*
* . when the very first queue is created, the queue is inserted into the
* list (as it could be the first queue in a possible burst)
*
* . if the current burst has not yet become large, and a queue Q that does
* not yet belong to the burst is activated shortly after the last time
* at which a new queue entered the burst list, then the function appends
* Q to the burst list
*
* . if, as a consequence of the previous step, the burst size reaches
* the large-burst threshold, then
*
* . all the queues in the burst list are marked as belonging to a
* large burst
*
* . the burst list is deleted; in fact, the burst list already served
* its purpose (keeping temporarily track of the queues in a burst,
* so as to be able to mark them as belonging to a large burst in the
* previous sub-step), and now is not needed any more
*
* . the device enters a large-burst mode
*
* . if a queue Q that does not belong to the burst is created while
* the device is in large-burst mode and shortly after the last time
* at which a queue either entered the burst list or was marked as
* belonging to the current large burst, then Q is immediately marked
* as belonging to a large burst.
*
* . if a queue Q that does not belong to the burst is created a while
* later, i.e., not shortly after, than the last time at which a queue
* either entered the burst list or was marked as belonging to the
* current large burst, then the current burst is deemed as finished and:
*
* . the large-burst mode is reset if set
*
* . the burst list is emptied
*
* . Q is inserted in the burst list, as Q may be the first queue
* in a possible new burst (then the burst list contains just Q
* after this step).
*/
static void bfq_handle_burst(
struct bfq_data *bfqd,
struct bfq_queue *bfqq)
{
/*
* If bfqq is already in the burst list or is part of a large
* burst, or finally has just been split, then there is
* nothing else to do.
*/
if (!hlist_unhashed(&bfqq->burst_list_node) ||
bfq_bfqq_in_large_burst(bfqq) ||
time_is_after_eq_jiffies(bfqq->split_time +
msecs_to_jiffies(10)))
return;
/*
* If bfqq's creation happens late enough, or bfqq belongs to
* a different group than the burst group, then the current
* burst is finished, and related data structures must be
* reset.
*
* In this respect, consider the special case where bfqq is
* the very first queue created after BFQ is selected for this
* device. In this case, last_ins_in_burst and
* burst_parent_entity are not yet significant when we get
* here. But it is easy to verify that, whether or not the
* following condition is true, bfqq will end up being
* inserted into the burst list. In particular the list will
* happen to contain only bfqq. And this is exactly what has
* to happen, as bfqq may be the first queue of the first
* burst.
*/
if (time_is_before_jiffies(bfqd->last_ins_in_burst +
bfqd->bfq_burst_interval) ||
bfqq->entity.parent != bfqd->burst_parent_entity) {
bfqd->large_burst =
false;
bfq_reset_burst_list(bfqd, bfqq);
goto end;
}
/*
* If we get here, then bfqq is being activated shortly after the
* last queue. So, if the current burst is also large, we can mark
* bfqq as belonging to this large burst immediately.
*/
if (bfqd->large_burst) {
bfq_mark_bfqq_in_large_burst(bfqq);
goto end;
}
/*
* If we get here, then a large-burst state has not yet been
* reached, but bfqq is being activated shortly after the last
* queue. Then we add bfqq to the burst.
*/
bfq_add_to_burst(bfqd, bfqq);
end:
/*
* At this point, bfqq either has been added to the current
* burst or has caused the current burst to terminate and a
* possible new burst to start. In particular, in the second
* case, bfqq has become the first queue in the possible new
* burst. In both cases last_ins_in_burst needs to be moved
* forward.
*/
bfqd->last_ins_in_burst = jiffies;
}
static int bfq_bfqq_budget_left(
struct bfq_queue *bfqq)
{
struct bfq_entity *entity = &bfqq->entity;
return entity->budget - entity->service;
}
/*
* If enough samples have been computed, return the current max budget
* stored in bfqd, which is dynamically updated according to the
* estimated disk peak rate; otherwise return the default max budget
*/
static int bfq_max_budget(
struct bfq_data *bfqd)
{
if (bfqd->budgets_assigned < bfq_stats_min_budgets)
return bfq_default_max_budget;
else
return bfqd->bfq_max_budget;
}
/*
* Return min budget, which is a fraction of the current or default
* max budget (trying with 1/32)
*/
static int bfq_min_budget(
struct bfq_data *bfqd)
{
if (bfqd->budgets_assigned < bfq_stats_min_budgets)
return bfq_default_max_budget / 32;
else
return bfqd->bfq_max_budget / 32;
}
/*
* The next function, invoked after the input queue bfqq switches from
* idle to busy, updates the budget of bfqq. The function also tells
* whether the in-service queue should be expired, by returning
* true. The purpose of expiring the in-service queue is to give bfqq
* the chance to possibly preempt the in-service queue, and the reason
* for preempting the in-service queue is to achieve one of the two
* goals below.
*
* 1. Guarantee to bfqq its reserved bandwidth even if bfqq has
* expired because it has remained idle. In particular, bfqq may have
* expired for one of the following two reasons:
*
* - BFQQE_NO_MORE_REQUESTS bfqq did not enjoy any device idling
* and did not make it to issue a new request before its last
* request was served;
*
* - BFQQE_TOO_IDLE bfqq did enjoy device idling, but did not issue
* a new request before the expiration of the idling-time.
*
* Even if bfqq has expired for one of the above reasons, the process
* associated with the queue may be however issuing requests greedily,
* and thus be sensitive to the bandwidth it receives (bfqq may have
* remained idle for other reasons: CPU high load, bfqq not enjoying
* idling, I/O throttling somewhere in the path from the process to
* the I/O scheduler, ...). But if, after every expiration for one of
* the above two reasons, bfqq has to wait for the service of at least
* one full budget of another queue before being served again, then
* bfqq is likely to get a much lower bandwidth or resource time than
* its reserved ones. To address this issue, two countermeasures need
* to be taken.
*
* First, the budget and the timestamps of bfqq need to be updated in
* a special way on bfqq reactivation: they need to be updated as if
* bfqq did not remain idle and did not expire. In fact, if they are
* computed as if bfqq expired and remained idle until reactivation,
* then the process associated with bfqq is treated as if, instead of
* being greedy, it stopped issuing requests when bfqq remained idle,
* and restarts issuing requests only on this reactivation. In other
* words, the scheduler does not help the process recover the "service
* hole" between bfqq expiration and reactivation. As a consequence,
* the process receives a lower bandwidth than its reserved one. In
* contrast, to recover this hole, the budget must be updated as if
* bfqq was not expired at all before this reactivation, i.e., it must
* be set to the value of the remaining budget when bfqq was
* expired. Along the same line, timestamps need to be assigned the
* value they had the last time bfqq was selected for service, i.e.,
* before last expiration. Thus timestamps need to be back-shifted
* with respect to their normal computation (see [1] for more details
* on this tricky aspect).
*
* Secondly, to allow the process to recover the hole, the in-service
* queue must be expired too, to give bfqq the chance to preempt it
* immediately. In fact, if bfqq has to wait for a full budget of the
* in-service queue to be completed, then it may become impossible to
* let the process recover the hole, even if the back-shifted
* timestamps of bfqq are lower than those of the in-service queue. If
* this happens for most or all of the holes, then the process may not
* receive its reserved bandwidth. In this respect, it is worth noting
* that, being the service of outstanding requests unpreemptible, a
* little fraction of the holes may however be unrecoverable, thereby
* causing a little loss of bandwidth.
*
* The last important point is detecting whether bfqq does need this
* bandwidth recovery. In this respect, the next function deems the
* process associated with bfqq greedy, and thus allows it to recover
* the hole, if: 1) the process is waiting for the arrival of a new
* request (which implies that bfqq expired for one of the above two
* reasons), and 2) such a request has arrived soon. The first
* condition is controlled through the flag non_blocking_wait_rq,
* while the second through the flag arrived_in_time. If both
* conditions hold, then the function computes the budget in the
* above-described special way, and signals that the in-service queue
* should be expired. Timestamp back-shifting is done later in
* __bfq_activate_entity.
*
* 2. Reduce latency. Even if timestamps are not backshifted to let
* the process associated with bfqq recover a service hole, bfqq may
* however happen to have, after being (re)activated, a lower finish
* timestamp than the in-service queue. That is, the next budget of
* bfqq may have to be completed before the one of the in-service
* queue. If this is the case, then preempting the in-service queue
* allows this goal to be achieved, apart from the unpreemptible,
* outstanding requests mentioned above.
*
* Unfortunately, regardless of which of the above two goals one wants
* to achieve, service trees need first to be updated to know whether
* the in-service queue must be preempted. To have service trees
* correctly updated, the in-service queue must be expired and
* rescheduled, and bfqq must be scheduled too. This is one of the
* most costly operations (in future versions, the scheduling
* mechanism may be re-designed in such a way to make it possible to
* know whether preemption is needed without needing to update service
* trees). In addition, queue preemptions almost always cause random
* I/O, which may in turn cause loss of throughput. Finally, there may
* even be no in-service queue when the next function is invoked (so,
* no queue to compare timestamps with). Because of these facts, the
* next function adopts the following simple scheme to avoid costly
* operations, too frequent preemptions and too many dependencies on
* the state of the scheduler: it requests the expiration of the
* in-service queue (unconditionally) only for queues that need to
* recover a hole. Then it delegates to other parts of the code the
* responsibility of handling the above case 2.
*/
static bool bfq_bfqq_update_budg_for_activation(
struct bfq_data *bfqd,
struct bfq_queue *bfqq,
bool arrived_in_time)
{
struct bfq_entity *entity = &bfqq->entity;
/*
* 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
* that timestamps need to be back-shifted (and is
* cleared right after).
*/
/*
* In next assignment we rely on that either
* entity->service or entity->budget are not updated
* on expiration if bfqq is empty (see
* __bfq_bfqq_recalc_budget). Thus both quantities
* remain unchanged after such an expiration, and the
* following statement therefore assigns to
* entity->budget the remaining budget on such an
* expiration.
*/
entity->budget = min_t(
unsigned long,
bfq_bfqq_budget_left(bfqq),
bfqq->max_budget);
/*
* At this point, we have used entity->service to get
* the budget left (needed for updating
* entity->budget). Thus we finally can, and have to,
* reset entity->service. The latter must be reset
* because bfqq would otherwise be charged again for
* the service it has received during its previous
* service slot(s).
*/
entity->service = 0;
return true;
}
/*
* We can finally complete expiration, by setting service to 0.
*/
entity->service = 0;
entity->budget = max_t(
unsigned long, bfqq->max_budget,
bfq_serv_to_charge(bfqq->next_rq, bfqq));
bfq_clear_bfqq_non_blocking_wait_rq(bfqq);
return false;
}
/*
* Return the farthest past time instant according to jiffies
* macros.
*/
static unsigned long bfq_smallest_from_now(
void)
{
return jiffies - MAX_JIFFY_OFFSET;
}
static void bfq_update_bfqq_wr_on_rq_arrival(
struct bfq_data *bfqd,
struct bfq_queue *bfqq,
unsigned int old_wr_coeff,
bool wr_or_deserves_wr,
bool interactive,
bool in_burst,
bool soft_rt)
{
if (old_wr_coeff == 1 && wr_or_deserves_wr) {
/* start a weight-raising period */
if (interactive) {
bfqq->service_from_wr = 0;
bfqq->wr_coeff = bfqd->bfq_wr_coeff;
bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
}
else {
/*
* No interactive weight raising in progress
* here: assign minus infinity to
* wr_start_at_switch_to_srt, to make sure
* that, at the end of the soft-real-time
* weight raising periods that is starting
* now, no interactive weight-raising period
* may be wrongly considered as still in
* progress (and thus actually started by
* mistake).
*/
bfqq->wr_start_at_switch_to_srt =
bfq_smallest_from_now();
bfqq->wr_coeff = bfqd->bfq_wr_coeff *
BFQ_SOFTRT_WEIGHT_FACTOR;
bfqq->wr_cur_max_time =
bfqd->bfq_wr_rt_max_time;
}
/*
* If needed, further reduce budget to make sure it is
* close to bfqq's backlog, so as to reduce the
* scheduling-error component due to a too large
* budget. Do not care about throughput consequences,
* but only about latency. Finally, do not assign a
* too small budget either, to avoid increasing
* latency by causing too frequent expirations.
*/
bfqq->entity.budget = min_t(
unsigned long,
bfqq->entity.budget,
2 * bfq_min_budget(bfqd));
}
else if (old_wr_coeff > 1) {
if (interactive) {
/* update wr coeff and duration */
bfqq->wr_coeff = bfqd->bfq_wr_coeff;
bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
}
else if (in_burst)
bfqq->wr_coeff = 1;
else if (soft_rt) {
/*
* The application is now or still meeting the
* requirements for being deemed soft rt. We
* can then correctly and safely (re)charge
* the weight-raising duration for the
* application with the weight-raising
* duration for soft rt applications.
*
* In particular, doing this recharge now, i.e.,
* before the weight-raising period for the
* application finishes, reduces the probability
* of the following negative scenario:
* 1) the weight of a soft rt application is
* raised at startup (as for any newly
* created application),
* 2) since the application is not interactive,
* at a certain time weight-raising is
* stopped for the application,
* 3) at that time the application happens to
* still have pending requests, and hence
* is destined to not have a chance to be
* deemed soft rt before these requests are
* completed (see the comments to the
* function bfq_bfqq_softrt_next_start()
* for details on soft rt detection),
* 4) these pending requests experience a high
* latency because the application is not
* weight-raised while they are pending.
*/
if (bfqq->wr_cur_max_time !=
bfqd->bfq_wr_rt_max_time) {
bfqq->wr_start_at_switch_to_srt =
bfqq->last_wr_start_finish;
bfqq->wr_cur_max_time =
bfqd->bfq_wr_rt_max_time;
bfqq->wr_coeff = bfqd->bfq_wr_coeff *
BFQ_SOFTRT_WEIGHT_FACTOR;
}
bfqq->last_wr_start_finish = jiffies;
}
}
}
static bool bfq_bfqq_idle_for_long_time(
struct bfq_data *bfqd,
struct bfq_queue *bfqq)
{
return bfqq->dispatched == 0 &&
time_is_before_jiffies(
bfqq->budget_timeout +
bfqd->bfq_wr_min_idle_time);
}
/*
* Return true if bfqq is in a higher priority class, or has a higher
* weight than the in-service queue.
*/
static bool bfq_bfqq_higher_class_or_weight(
struct bfq_queue *bfqq,
struct bfq_queue *in_serv_bfqq)
{
int bfqq_weight, in_serv_weight;
if (bfqq->ioprio_class < in_serv_bfqq->ioprio_class)
return true;
if (in_serv_bfqq->entity.parent == bfqq->entity.parent) {
bfqq_weight = bfqq->entity.weight;
in_serv_weight = in_serv_bfqq->entity.weight;
}
else {
if (bfqq->entity.parent)
bfqq_weight = bfqq->entity.parent->weight;
else
bfqq_weight = bfqq->entity.weight;
if (in_serv_bfqq->entity.parent)
in_serv_weight = in_serv_bfqq->entity.parent->weight;
else
in_serv_weight = in_serv_bfqq->entity.weight;
}
return bfqq_weight > in_serv_weight;
}
/*
* Get the index of the actuator that will serve bio.
*/
static unsigned int bfq_actuator_index(
struct bfq_data *bfqd,
struct bio *bio)
{
unsigned int i;
sector_t end;
/* no search needed if one or zero ranges present */
if (bfqd->num_actuators == 1)
return 0;
/* bio_end_sector(bio) gives the sector after the last one */
end = bio_end_sector(bio) - 1;
--> --------------------
--> maximum size reached
--> --------------------
