#define BFQ_DEFAULT_QUEUE_IOPRIO 4
-#define BFQ_WEIGHT_LEGACY_DFL 100
#define BFQ_DEFAULT_GRP_IOPRIO 0
#define BFQ_DEFAULT_GRP_CLASS IOPRIO_CLASS_BE
*/
#define BFQ_SOFTRT_WEIGHT_FACTOR 100
+/*
+ * Maximum number of actuators supported. This constant is used simply
+ * to define the size of the static array that will contain
+ * per-actuator data. The current value is hopefully a good upper
+ * bound to the possible number of actuators of any actual drive.
+ */
+#define BFQ_MAX_ACTUATORS 8
+
struct bfq_entity;
/**
/* flag, set to request a weight, ioprio or ioprio_class change */
int prio_changed;
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
/* flag, set if the entity is counted in groups_with_pending_reqs */
bool in_groups_with_pending_reqs;
+#endif
/* last child queue of entity created (for non-leaf entities) */
struct bfq_queue *last_bfqq_created;
* struct bfq_queue - leaf schedulable entity.
*
* A bfq_queue is a leaf request queue; it can be associated with an
- * io_context or more, if it is async or shared between cooperating
- * processes. @cgroup holds a reference to the cgroup, to be sure that it
- * does not disappear while a bfqq still references it (mostly to avoid
- * races between request issuing and task migration followed by cgroup
- * destruction).
- * All the fields are protected by the queue lock of the containing bfqd.
+ * io_context or more, if it is async or shared between cooperating
+ * processes. Besides, it contains I/O requests for only one actuator
+ * (an io_context is associated with a different bfq_queue for each
+ * actuator it generates I/O for). @cgroup holds a reference to the
+ * cgroup, to be sure that it does not disappear while a bfqq still
+ * references it (mostly to avoid races between request issuing and
+ * task migration followed by cgroup destruction). All the fields are
+ * protected by the queue lock of the containing bfqd.
*/
struct bfq_queue {
/* reference counter */
unsigned long split_time; /* time of last split */
unsigned long first_IO_time; /* time of first I/O for this queue */
-
unsigned long creation_time; /* when this queue is created */
- /* max service rate measured so far */
- u32 max_service_rate;
-
/*
* Pointer to the waker queue for this queue, i.e., to the
* queue Q such that this queue happens to get new I/O right
* the woken queues when this queue exits.
*/
struct hlist_head woken_list;
+
+ /* index of the actuator this queue is associated with */
+ unsigned int actuator_idx;
};
/**
- * struct bfq_io_cq - per (request_queue, io_context) structure.
- */
-struct bfq_io_cq {
- /* associated io_cq structure */
- struct io_cq icq; /* must be the first member */
- /* array of two process queues, the sync and the async */
- struct bfq_queue *bfqq[2];
- /* per (request_queue, blkcg) ioprio */
- int ioprio;
-#ifdef CONFIG_BFQ_GROUP_IOSCHED
- uint64_t blkcg_serial_nr; /* the current blkcg serial */
-#endif
+* struct bfq_data - bfqq data unique and persistent for associated bfq_io_cq
+*/
+struct bfq_iocq_bfqq_data {
/*
* Snapshot of the has_short_time flag before merging; taken
- * to remember its value while the queue is merged, so as to
+ * to remember its values while the queue is merged, so as to
* be able to restore it in case of split.
*/
bool saved_has_short_ttime;
u64 saved_tot_idle_time;
/*
- * Same purpose as the previous fields for the value of the
+ * Same purpose as the previous fields for the values of the
* field keeping the queue's belonging to a large burst
*/
bool saved_in_large_burst;
struct bfq_queue *stable_merge_bfqq;
bool stably_merged; /* non splittable if true */
+};
+
+/**
+ * struct bfq_io_cq - per (request_queue, io_context) structure.
+ */
+struct bfq_io_cq {
+ /* associated io_cq structure */
+ struct io_cq icq; /* must be the first member */
+ /*
+ * Matrix of associated process queues: first row for async
+ * queues, second row sync queues. Each row contains one
+ * column for each actuator. An I/O request generated by the
+ * process is inserted into the queue pointed by bfqq[i][j] if
+ * the request is to be served by the j-th actuator of the
+ * drive, where i==0 or i==1, depending on whether the request
+ * is async or sync. So there is a distinct queue for each
+ * actuator.
+ */
+ struct bfq_queue *bfqq[2][BFQ_MAX_ACTUATORS];
+ /* per (request_queue, blkcg) ioprio */
+ int ioprio;
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+ uint64_t blkcg_serial_nr; /* the current blkcg serial */
+#endif
+
+ /*
+ * Persistent data for associated synchronous process queues
+ * (one queue per actuator, see field bfqq above). In
+ * particular, each of these queues may undergo a merge.
+ */
+ struct bfq_iocq_bfqq_data bfqq_data[BFQ_MAX_ACTUATORS];
+
unsigned int requests; /* Number of requests this process has in flight */
};
*/
struct rb_root_cached queue_weights_tree;
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
/*
- * Number of groups with at least one descendant process that
+ * Number of groups with at least one process that
* has at least one request waiting for completion. Note that
* this accounts for also requests already dispatched, but not
* yet completed. Therefore this number of groups may differ
* (be larger) than the number of active groups, as a group is
* considered active only if its corresponding entity has
- * descendant queues with at least one request queued. This
+ * queues with at least one request queued. This
* number is used to decide whether a scenario is symmetric.
* For a detailed explanation see comments on the computation
* of the variable asymmetric_scenario in the function
* bfq_better_to_idle().
*
* However, it is hard to compute this number exactly, for
- * groups with multiple descendant processes. Consider a group
- * that is inactive, i.e., that has no descendant process with
+ * groups with multiple processes. Consider a group
+ * that is inactive, i.e., that has no process with
* pending I/O inside BFQ queues. Then suppose that
* num_groups_with_pending_reqs is still accounting for this
- * group, because the group has descendant processes with some
+ * group, because the group has processes with some
* I/O request still in flight. num_groups_with_pending_reqs
* should be decremented when the in-flight request of the
- * last descendant process is finally completed (assuming that
+ * last process is finally completed (assuming that
* nothing else has changed for the group in the meantime, in
* terms of composition of the group and active/inactive state of child
* groups and processes). To accomplish this, an additional
* we resort to the following tradeoff between simplicity and
* accuracy: for an inactive group that is still counted in
* num_groups_with_pending_reqs, we decrement
- * num_groups_with_pending_reqs when the first descendant
+ * num_groups_with_pending_reqs when the first
* process of the group remains with no request waiting for
* completion.
*
* carefulness: to avoid multiple decrements, we flag a group,
* more precisely an entity representing a group, as still
* counted in num_groups_with_pending_reqs when it becomes
- * inactive. Then, when the first descendant queue of the
+ * inactive. Then, when the first queue of the
* entity remains with no request waiting for completion,
* num_groups_with_pending_reqs is decremented, and this flag
* is reset. After this flag is reset for the entity,
* num_groups_with_pending_reqs won't be decremented any
- * longer in case a new descendant queue of the entity remains
+ * longer in case a new queue of the entity remains
* with no request waiting for completion.
*/
unsigned int num_groups_with_pending_reqs;
+#endif
/*
* Per-class (RT, BE, IDLE) number of bfq_queues containing
/* number of queued requests */
int queued;
/* number of requests dispatched and waiting for completion */
- int rq_in_driver;
+ int tot_rq_in_driver;
+ /*
+ * number of requests dispatched and waiting for completion
+ * for each actuator
+ */
+ int rq_in_driver[BFQ_MAX_ACTUATORS];
/* true if the device is non rotational and performs queueing */
bool nonrot_with_queueing;
/* maximum budget allotted to a bfq_queue before rescheduling */
int bfq_max_budget;
- /* list of all the bfq_queues active on the device */
- struct list_head active_list;
+ /*
+ * List of all the bfq_queues active for a specific actuator
+ * on the device. Keeping active queues separate on a
+ * per-actuator basis helps implementing per-actuator
+ * injection more efficiently.
+ */
+ struct list_head active_list[BFQ_MAX_ACTUATORS];
/* list of all the bfq_queues idle on the device */
struct list_head idle_list;
* is multiplied.
*/
unsigned int bfq_wr_coeff;
- /* maximum duration of a weight-raising period (jiffies) */
- unsigned int bfq_wr_max_time;
/* Maximum weight-raising duration for soft real-time processes */
unsigned int bfq_wr_rt_max_time;
*/
unsigned int word_depths[2][2];
unsigned int full_depth_shift;
+
+ /*
+ * Number of independent actuators. This is equal to 1 in
+ * case of single-actuator drives.
+ */
+ unsigned int num_actuators;
+ /*
+ * Disk independent access ranges for each actuator
+ * in this device.
+ */
+ sector_t sector[BFQ_MAX_ACTUATORS];
+ sector_t nr_sectors[BFQ_MAX_ACTUATORS];
+ struct blk_independent_access_range ia_ranges[BFQ_MAX_ACTUATORS];
+
+ /*
+ * If the number of I/O requests queued in the device for a
+ * given actuator is below next threshold, then the actuator
+ * is deemed as underutilized. If this condition is found to
+ * hold for some actuator upon a dispatch, but (i) the
+ * in-service queue does not contain I/O for that actuator,
+ * while (ii) some other queue does contain I/O for that
+ * actuator, then the head I/O request of the latter queue is
+ * returned (injected), instead of the head request of the
+ * currently in-service queue.
+ *
+ * We set the threshold, empirically, to the minimum possible
+ * value for which an actuator is fully utilized, or close to
+ * be fully utilized. By doing so, injected I/O 'steals' as
+ * few drive-queue slots as possibile to the in-service
+ * queue. This reduces as much as possible the probability
+ * that the service of I/O from the in-service bfq_queue gets
+ * delayed because of slot exhaustion, i.e., because all the
+ * slots of the drive queue are filled with I/O injected from
+ * other queues (NCQ provides for 32 slots).
+ */
+ unsigned int actuator_load_threshold;
};
enum bfqq_state_flags {
char blkg_path[128];
/* reference counter (see comments in bfq_bic_update_cgroup) */
- int ref;
- /* Is bfq_group still online? */
- bool online;
+ refcount_t ref;
struct bfq_entity entity;
struct bfq_sched_data sched_data;
- void *bfqd;
+ struct bfq_data *bfqd;
- struct bfq_queue *async_bfqq[2][IOPRIO_NR_LEVELS];
- struct bfq_queue *async_idle_bfqq;
+ struct bfq_queue *async_bfqq[2][IOPRIO_NR_LEVELS][BFQ_MAX_ACTUATORS];
+ struct bfq_queue *async_idle_bfqq[BFQ_MAX_ACTUATORS];
struct bfq_entity *my_entity;
int active_entities;
+ int num_queues_with_pending_reqs;
struct rb_root rq_pos_tree;
struct bfq_entity entity;
struct bfq_sched_data sched_data;
- struct bfq_queue *async_bfqq[2][IOPRIO_NR_LEVELS];
- struct bfq_queue *async_idle_bfqq;
+ struct bfq_queue *async_bfqq[2][IOPRIO_NR_LEVELS][BFQ_MAX_ACTUATORS];
+ struct bfq_queue *async_idle_bfqq[BFQ_MAX_ACTUATORS];
struct rb_root rq_pos_tree;
};
extern const int bfq_timeout;
-struct bfq_queue *bic_to_bfqq(struct bfq_io_cq *bic, bool is_sync);
-void bic_set_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq, bool is_sync);
+struct bfq_queue *bic_to_bfqq(struct bfq_io_cq *bic, bool is_sync,
+ unsigned int actuator_idx);
+void bic_set_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq, bool is_sync,
+ unsigned int actuator_idx);
struct bfq_data *bic_to_bfqd(struct bfq_io_cq *bic);
void bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq);
-void bfq_weights_tree_add(struct bfq_data *bfqd, struct bfq_queue *bfqq,
- struct rb_root_cached *root);
-void __bfq_weights_tree_remove(struct bfq_data *bfqd,
- struct bfq_queue *bfqq,
- struct rb_root_cached *root);
-void bfq_weights_tree_remove(struct bfq_data *bfqd,
- struct bfq_queue *bfqq);
+void bfq_weights_tree_add(struct bfq_queue *bfqq);
+void bfq_weights_tree_remove(struct bfq_queue *bfqq);
void bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq,
bool compensate, enum bfqq_expiration reason);
void bfq_put_queue(struct bfq_queue *bfqq);
/* ---------------- cgroups-support interface ---------------- */
void bfqg_stats_update_legacy_io(struct request_queue *q, struct request *rq);
-void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq,
- blk_opf_t opf);
void bfqg_stats_update_io_remove(struct bfq_group *bfqg, blk_opf_t opf);
void bfqg_stats_update_io_merged(struct bfq_group *bfqg, blk_opf_t opf);
void bfqg_stats_update_completion(struct bfq_group *bfqg, u64 start_time_ns,
u64 io_start_time_ns, blk_opf_t opf);
void bfqg_stats_update_dequeue(struct bfq_group *bfqg);
-void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg);
-void bfqg_stats_update_idle_time(struct bfq_group *bfqg);
void bfqg_stats_set_start_idle_time(struct bfq_group *bfqg);
-void bfqg_stats_update_avg_queue_size(struct bfq_group *bfqg);
void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
struct bfq_group *bfqg);
+#ifdef CONFIG_BFQ_CGROUP_DEBUG
+void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq,
+ blk_opf_t opf);
+void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg);
+void bfqg_stats_update_idle_time(struct bfq_group *bfqg);
+void bfqg_stats_update_avg_queue_size(struct bfq_group *bfqg);
+#endif
+
void bfq_init_entity(struct bfq_entity *entity, struct bfq_group *bfqg);
void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio);
void bfq_end_wr_async(struct bfq_data *bfqd);
void bfq_activate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq);
void bfq_requeue_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
bool expiration);
-void bfq_del_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq,
- bool expiration);
-void bfq_add_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq);
+void bfq_del_bfqq_busy(struct bfq_queue *bfqq, bool expiration);
+void bfq_add_bfqq_busy(struct bfq_queue *bfqq);
+void bfq_add_bfqq_in_groups_with_pending_reqs(struct bfq_queue *bfqq);
+void bfq_del_bfqq_in_groups_with_pending_reqs(struct bfq_queue *bfqq);
/* --------------- end of interface of B-WF2Q+ ---------------- */
projects / linux-2.6-microblaze.git / blobdiff