#include <linux/elevator.h>
#include <linux/rbtree.h>
#include <linux/ioprio.h>
+#include <linux/blktrace_api.h>
/*
* tunables
#define CFQ_MIN_TT (2)
#define CFQ_SLICE_SCALE (5)
+#define CFQ_HW_QUEUE_MIN (5)
#define RQ_CIC(rq) \
((struct cfq_io_context *) (rq)->elevator_private)
-#define RQ_CFQQ(rq) ((rq)->elevator_private2)
+#define RQ_CFQQ(rq) (struct cfq_queue *) ((rq)->elevator_private2)
static struct kmem_cache *cfq_pool;
static struct kmem_cache *cfq_ioc_pool;
#define cfq_class_idle(cfqq) ((cfqq)->ioprio_class == IOPRIO_CLASS_IDLE)
#define cfq_class_rt(cfqq) ((cfqq)->ioprio_class == IOPRIO_CLASS_RT)
-#define ASYNC (0)
-#define SYNC (1)
-
#define sample_valid(samples) ((samples) > 80)
/*
* rr list of queues with requests and the count of them
*/
struct cfq_rb_root service_tree;
+
+ /*
+ * Each priority tree is sorted by next_request position. These
+ * trees are used when determining if two or more queues are
+ * interleaving requests (see cfq_close_cooperator).
+ */
+ struct rb_root prio_trees[CFQ_PRIO_LISTS];
+
unsigned int busy_queues;
+ /*
+ * Used to track any pending rt requests so we can pre-empt current
+ * non-RT cfqq in service when this value is non-zero.
+ */
+ unsigned int busy_rt_queues;
int rq_in_driver;
int sync_flight;
+
+ /*
+ * queue-depth detection
+ */
+ int rq_queued;
int hw_tag;
+ int hw_tag_samples;
+ int rq_in_driver_peak;
/*
* idle window management
struct rb_node rb_node;
/* service_tree key */
unsigned long rb_key;
+ /* prio tree member */
+ struct rb_node p_node;
+ /* prio tree root we belong to, if any */
+ struct rb_root *p_root;
/* sorted list of pending requests */
struct rb_root sort_list;
/* if fifo isn't expired, next request to serve */
unsigned long slice_end;
long slice_resid;
+ unsigned int slice_dispatch;
/* pending metadata requests */
int meta_pending;
unsigned short ioprio, org_ioprio;
unsigned short ioprio_class, org_ioprio_class;
+ pid_t pid;
};
enum cfqq_state_flags {
CFQ_CFQQ_FLAG_on_rr = 0, /* on round-robin busy list */
CFQ_CFQQ_FLAG_wait_request, /* waiting for a request */
+ CFQ_CFQQ_FLAG_must_dispatch, /* must be allowed a dispatch */
CFQ_CFQQ_FLAG_must_alloc, /* must be allowed rq alloc */
CFQ_CFQQ_FLAG_must_alloc_slice, /* per-slice must_alloc flag */
- CFQ_CFQQ_FLAG_must_dispatch, /* must dispatch, even if expired */
CFQ_CFQQ_FLAG_fifo_expire, /* FIFO checked in this slice */
CFQ_CFQQ_FLAG_idle_window, /* slice idling enabled */
CFQ_CFQQ_FLAG_prio_changed, /* task priority has changed */
- CFQ_CFQQ_FLAG_queue_new, /* queue never been serviced */
CFQ_CFQQ_FLAG_slice_new, /* no requests dispatched in slice */
CFQ_CFQQ_FLAG_sync, /* synchronous queue */
+ CFQ_CFQQ_FLAG_coop, /* has done a coop jump of the queue */
};
#define CFQ_CFQQ_FNS(name) \
CFQ_CFQQ_FNS(on_rr);
CFQ_CFQQ_FNS(wait_request);
+CFQ_CFQQ_FNS(must_dispatch);
CFQ_CFQQ_FNS(must_alloc);
CFQ_CFQQ_FNS(must_alloc_slice);
-CFQ_CFQQ_FNS(must_dispatch);
CFQ_CFQQ_FNS(fifo_expire);
CFQ_CFQQ_FNS(idle_window);
CFQ_CFQQ_FNS(prio_changed);
-CFQ_CFQQ_FNS(queue_new);
CFQ_CFQQ_FNS(slice_new);
CFQ_CFQQ_FNS(sync);
+CFQ_CFQQ_FNS(coop);
#undef CFQ_CFQQ_FNS
+#define cfq_log_cfqq(cfqd, cfqq, fmt, args...) \
+ blk_add_trace_msg((cfqd)->queue, "cfq%d " fmt, (cfqq)->pid, ##args)
+#define cfq_log(cfqd, fmt, args...) \
+ blk_add_trace_msg((cfqd)->queue, "cfq " fmt, ##args)
+
static void cfq_dispatch_insert(struct request_queue *, struct request *);
static struct cfq_queue *cfq_get_queue(struct cfq_data *, int,
struct io_context *, gfp_t);
*/
static inline void cfq_schedule_dispatch(struct cfq_data *cfqd)
{
- if (cfqd->busy_queues)
- kblockd_schedule_work(&cfqd->unplug_work);
+ if (cfqd->busy_queues) {
+ cfq_log(cfqd, "schedule dispatch");
+ kblockd_schedule_work(cfqd->queue, &cfqd->unplug_work);
+ }
}
static int cfq_queue_empty(struct request_queue *q)
cfq_set_prio_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
cfqq->slice_end = cfq_prio_to_slice(cfqd, cfqq) + jiffies;
+ cfq_log_cfqq(cfqd, cfqq, "set_slice=%lu", cfqq->slice_end - jiffies);
}
/*
return NULL;
}
+static void rb_erase_init(struct rb_node *n, struct rb_root *root)
+{
+ rb_erase(n, root);
+ RB_CLEAR_NODE(n);
+}
+
static void cfq_rb_erase(struct rb_node *n, struct cfq_rb_root *root)
{
if (root->left == n)
root->left = NULL;
-
- rb_erase(n, &root->rb);
- RB_CLEAR_NODE(n);
+ rb_erase_init(n, &root->rb);
}
/*
* requests waiting to be processed. It is sorted in the order that
* we will service the queues.
*/
-static void cfq_service_tree_add(struct cfq_data *cfqd,
- struct cfq_queue *cfqq, int add_front)
+static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
+ int add_front)
{
struct rb_node **p, *parent;
struct cfq_queue *__cfqq;
rb_insert_color(&cfqq->rb_node, &cfqd->service_tree.rb);
}
+static struct cfq_queue *
+cfq_prio_tree_lookup(struct cfq_data *cfqd, struct rb_root *root,
+ sector_t sector, struct rb_node **ret_parent,
+ struct rb_node ***rb_link)
+{
+ struct rb_node **p, *parent;
+ struct cfq_queue *cfqq = NULL;
+
+ parent = NULL;
+ p = &root->rb_node;
+ while (*p) {
+ struct rb_node **n;
+
+ parent = *p;
+ cfqq = rb_entry(parent, struct cfq_queue, p_node);
+
+ /*
+ * Sort strictly based on sector. Smallest to the left,
+ * largest to the right.
+ */
+ if (sector > cfqq->next_rq->sector)
+ n = &(*p)->rb_right;
+ else if (sector < cfqq->next_rq->sector)
+ n = &(*p)->rb_left;
+ else
+ break;
+ p = n;
+ cfqq = NULL;
+ }
+
+ *ret_parent = parent;
+ if (rb_link)
+ *rb_link = p;
+ return cfqq;
+}
+
+static void cfq_prio_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+{
+ struct rb_node **p, *parent;
+ struct cfq_queue *__cfqq;
+
+ if (cfqq->p_root) {
+ rb_erase(&cfqq->p_node, cfqq->p_root);
+ cfqq->p_root = NULL;
+ }
+
+ if (cfq_class_idle(cfqq))
+ return;
+ if (!cfqq->next_rq)
+ return;
+
+ cfqq->p_root = &cfqd->prio_trees[cfqq->org_ioprio];
+ __cfqq = cfq_prio_tree_lookup(cfqd, cfqq->p_root, cfqq->next_rq->sector,
+ &parent, &p);
+ if (!__cfqq) {
+ rb_link_node(&cfqq->p_node, parent, p);
+ rb_insert_color(&cfqq->p_node, cfqq->p_root);
+ } else
+ cfqq->p_root = NULL;
+}
+
/*
* Update cfqq's position in the service tree.
*/
/*
* Resorting requires the cfqq to be on the RR list already.
*/
- if (cfq_cfqq_on_rr(cfqq))
+ if (cfq_cfqq_on_rr(cfqq)) {
cfq_service_tree_add(cfqd, cfqq, 0);
+ cfq_prio_tree_add(cfqd, cfqq);
+ }
}
/*
*/
static void cfq_add_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
+ cfq_log_cfqq(cfqd, cfqq, "add_to_rr");
BUG_ON(cfq_cfqq_on_rr(cfqq));
cfq_mark_cfqq_on_rr(cfqq);
cfqd->busy_queues++;
+ if (cfq_class_rt(cfqq))
+ cfqd->busy_rt_queues++;
cfq_resort_rr_list(cfqd, cfqq);
}
*/
static void cfq_del_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
+ cfq_log_cfqq(cfqd, cfqq, "del_from_rr");
BUG_ON(!cfq_cfqq_on_rr(cfqq));
cfq_clear_cfqq_on_rr(cfqq);
if (!RB_EMPTY_NODE(&cfqq->rb_node))
cfq_rb_erase(&cfqq->rb_node, &cfqd->service_tree);
+ if (cfqq->p_root) {
+ rb_erase(&cfqq->p_node, cfqq->p_root);
+ cfqq->p_root = NULL;
+ }
BUG_ON(!cfqd->busy_queues);
cfqd->busy_queues--;
+ if (cfq_class_rt(cfqq))
+ cfqd->busy_rt_queues--;
}
/*
{
struct cfq_queue *cfqq = RQ_CFQQ(rq);
struct cfq_data *cfqd = cfqq->cfqd;
- struct request *__alias;
+ struct request *__alias, *prev;
cfqq->queued[rq_is_sync(rq)]++;
/*
* check if this request is a better next-serve candidate
*/
+ prev = cfqq->next_rq;
cfqq->next_rq = cfq_choose_req(cfqd, cfqq->next_rq, rq);
+
+ /*
+ * adjust priority tree position, if ->next_rq changes
+ */
+ if (prev != cfqq->next_rq)
+ cfq_prio_tree_add(cfqd, cfqq);
+
BUG_ON(!cfqq->next_rq);
}
struct cfq_data *cfqd = q->elevator->elevator_data;
cfqd->rq_in_driver++;
-
- /*
- * If the depth is larger 1, it really could be queueing. But lets
- * make the mark a little higher - idling could still be good for
- * low queueing, and a low queueing number could also just indicate
- * a SCSI mid layer like behaviour where limit+1 is often seen.
- */
- if (!cfqd->hw_tag && cfqd->rq_in_driver > 4)
- cfqd->hw_tag = 1;
+ cfq_log_cfqq(cfqd, RQ_CFQQ(rq), "activate rq, drv=%d",
+ cfqd->rq_in_driver);
cfqd->last_position = rq->hard_sector + rq->hard_nr_sectors;
}
WARN_ON(!cfqd->rq_in_driver);
cfqd->rq_in_driver--;
+ cfq_log_cfqq(cfqd, RQ_CFQQ(rq), "deactivate rq, drv=%d",
+ cfqd->rq_in_driver);
}
static void cfq_remove_request(struct request *rq)
list_del_init(&rq->queuelist);
cfq_del_rq_rb(rq);
+ cfqq->cfqd->rq_queued--;
if (rq_is_meta(rq)) {
WARN_ON(!cfqq->meta_pending);
cfqq->meta_pending--;
struct cfq_queue *cfqq)
{
if (cfqq) {
+ cfq_log_cfqq(cfqd, cfqq, "set_active");
cfqq->slice_end = 0;
+ cfqq->slice_dispatch = 0;
+
+ cfq_clear_cfqq_wait_request(cfqq);
+ cfq_clear_cfqq_must_dispatch(cfqq);
cfq_clear_cfqq_must_alloc_slice(cfqq);
cfq_clear_cfqq_fifo_expire(cfqq);
cfq_mark_cfqq_slice_new(cfqq);
- cfq_clear_cfqq_queue_new(cfqq);
+
+ del_timer(&cfqd->idle_slice_timer);
}
cfqd->active_queue = cfqq;
__cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq,
int timed_out)
{
+ cfq_log_cfqq(cfqd, cfqq, "slice expired t=%d", timed_out);
+
if (cfq_cfqq_wait_request(cfqq))
del_timer(&cfqd->idle_slice_timer);
- cfq_clear_cfqq_must_dispatch(cfqq);
cfq_clear_cfqq_wait_request(cfqq);
/*
* store what was left of this slice, if the queue idled/timed out
*/
- if (timed_out && !cfq_cfqq_slice_new(cfqq))
+ if (timed_out && !cfq_cfqq_slice_new(cfqq)) {
cfqq->slice_resid = cfqq->slice_end - jiffies;
+ cfq_log_cfqq(cfqd, cfqq, "resid=%ld", cfqq->slice_resid);
+ }
cfq_resort_rr_list(cfqd, cfqq);
/*
* Get and set a new active queue for service.
*/
-static struct cfq_queue *cfq_set_active_queue(struct cfq_data *cfqd)
+static struct cfq_queue *cfq_set_active_queue(struct cfq_data *cfqd,
+ struct cfq_queue *cfqq)
{
- struct cfq_queue *cfqq;
+ if (!cfqq) {
+ cfqq = cfq_get_next_queue(cfqd);
+ if (cfqq)
+ cfq_clear_cfqq_coop(cfqq);
+ }
- cfqq = cfq_get_next_queue(cfqd);
__cfq_set_active_queue(cfqd, cfqq);
return cfqq;
}
return cfqd->last_position - rq->sector;
}
+#define CIC_SEEK_THR 8 * 1024
+#define CIC_SEEKY(cic) ((cic)->seek_mean > CIC_SEEK_THR)
+
static inline int cfq_rq_close(struct cfq_data *cfqd, struct request *rq)
{
struct cfq_io_context *cic = cfqd->active_cic;
+ sector_t sdist = cic->seek_mean;
if (!sample_valid(cic->seek_samples))
- return 0;
+ sdist = CIC_SEEK_THR;
- return cfq_dist_from_last(cfqd, rq) <= cic->seek_mean;
+ return cfq_dist_from_last(cfqd, rq) <= sdist;
}
-static int cfq_close_cooperator(struct cfq_data *cfq_data,
- struct cfq_queue *cfqq)
+static struct cfq_queue *cfqq_close(struct cfq_data *cfqd,
+ struct cfq_queue *cur_cfqq)
{
+ struct rb_root *root = &cfqd->prio_trees[cur_cfqq->org_ioprio];
+ struct rb_node *parent, *node;
+ struct cfq_queue *__cfqq;
+ sector_t sector = cfqd->last_position;
+
+ if (RB_EMPTY_ROOT(root))
+ return NULL;
+
+ /*
+ * First, if we find a request starting at the end of the last
+ * request, choose it.
+ */
+ __cfqq = cfq_prio_tree_lookup(cfqd, root, sector, &parent, NULL);
+ if (__cfqq)
+ return __cfqq;
+
+ /*
+ * If the exact sector wasn't found, the parent of the NULL leaf
+ * will contain the closest sector.
+ */
+ __cfqq = rb_entry(parent, struct cfq_queue, p_node);
+ if (cfq_rq_close(cfqd, __cfqq->next_rq))
+ return __cfqq;
+
+ if (__cfqq->next_rq->sector < sector)
+ node = rb_next(&__cfqq->p_node);
+ else
+ node = rb_prev(&__cfqq->p_node);
+ if (!node)
+ return NULL;
+
+ __cfqq = rb_entry(node, struct cfq_queue, p_node);
+ if (cfq_rq_close(cfqd, __cfqq->next_rq))
+ return __cfqq;
+
+ return NULL;
+}
+
+/*
+ * cfqd - obvious
+ * cur_cfqq - passed in so that we don't decide that the current queue is
+ * closely cooperating with itself.
+ *
+ * So, basically we're assuming that that cur_cfqq has dispatched at least
+ * one request, and that cfqd->last_position reflects a position on the disk
+ * associated with the I/O issued by cur_cfqq. I'm not sure this is a valid
+ * assumption.
+ */
+static struct cfq_queue *cfq_close_cooperator(struct cfq_data *cfqd,
+ struct cfq_queue *cur_cfqq,
+ int probe)
+{
+ struct cfq_queue *cfqq;
+
+ /*
+ * A valid cfq_io_context is necessary to compare requests against
+ * the seek_mean of the current cfqq.
+ */
+ if (!cfqd->active_cic)
+ return NULL;
+
/*
* We should notice if some of the queues are cooperating, eg
* working closely on the same area of the disk. In that case,
* we can group them together and don't waste time idling.
*/
- return 0;
-}
+ cfqq = cfqq_close(cfqd, cur_cfqq);
+ if (!cfqq)
+ return NULL;
-#define CIC_SEEKY(cic) ((cic)->seek_mean > (8 * 1024))
+ if (cfq_cfqq_coop(cfqq))
+ return NULL;
+
+ if (!probe)
+ cfq_mark_cfqq_coop(cfqq);
+ return cfqq;
+}
static void cfq_arm_slice_timer(struct cfq_data *cfqd)
{
struct cfq_io_context *cic;
unsigned long sl;
+ /*
+ * SSD device without seek penalty, disable idling. But only do so
+ * for devices that support queuing, otherwise we still have a problem
+ * with sync vs async workloads.
+ */
+ if (blk_queue_nonrot(cfqd->queue) && cfqd->hw_tag)
+ return;
+
WARN_ON(!RB_EMPTY_ROOT(&cfqq->sort_list));
WARN_ON(cfq_cfqq_slice_new(cfqq));
return;
/*
- * task has exited, don't wait
+ * still requests with the driver, don't idle
*/
- cic = cfqd->active_cic;
- if (!cic || !atomic_read(&cic->ioc->nr_tasks))
+ if (cfqd->rq_in_driver)
return;
/*
- * See if this prio level has a good candidate
+ * task has exited, don't wait
*/
- if (cfq_close_cooperator(cfqd, cfqq) &&
- (sample_valid(cic->ttime_samples) && cic->ttime_mean > 2))
+ cic = cfqd->active_cic;
+ if (!cic || !atomic_read(&cic->ioc->nr_tasks))
return;
- cfq_mark_cfqq_must_dispatch(cfqq);
cfq_mark_cfqq_wait_request(cfqq);
/*
sl = min(sl, msecs_to_jiffies(CFQ_MIN_TT));
mod_timer(&cfqd->idle_slice_timer, jiffies + sl);
+ cfq_log_cfqq(cfqd, cfqq, "arm_idle: %lu", sl);
}
/*
struct cfq_data *cfqd = q->elevator->elevator_data;
struct cfq_queue *cfqq = RQ_CFQQ(rq);
+ cfq_log_cfqq(cfqd, cfqq, "dispatch_insert");
+
cfq_remove_request(rq);
cfqq->dispatched++;
elv_dispatch_sort(q, rq);
rq = rq_entry_fifo(cfqq->fifo.next);
if (time_before(jiffies, rq->start_time + cfqd->cfq_fifo_expire[fifo]))
- return NULL;
+ rq = NULL;
+ cfq_log_cfqq(cfqd, cfqq, "fifo=%p", rq);
return rq;
}
*/
static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
{
- struct cfq_queue *cfqq;
+ struct cfq_queue *cfqq, *new_cfqq = NULL;
cfqq = cfqd->active_queue;
if (!cfqq)
/*
* The active queue has run out of time, expire it and select new.
*/
- if (cfq_slice_used(cfqq))
+ if (cfq_slice_used(cfqq) && !cfq_cfqq_must_dispatch(cfqq))
goto expire;
/*
+ * If we have a RT cfqq waiting, then we pre-empt the current non-rt
+ * cfqq.
+ */
+ if (!cfq_class_rt(cfqq) && cfqd->busy_rt_queues) {
+ /*
+ * We simulate this as cfqq timed out so that it gets to bank
+ * the remaining of its time slice.
+ */
+ cfq_log_cfqq(cfqd, cfqq, "preempt");
+ cfq_slice_expired(cfqd, 1);
+ goto new_queue;
+ }
+
+ /*
* The active queue has requests and isn't expired, allow it to
* dispatch.
*/
goto keep_queue;
/*
+ * If another queue has a request waiting within our mean seek
+ * distance, let it run. The expire code will check for close
+ * cooperators and put the close queue at the front of the service
+ * tree.
+ */
+ new_cfqq = cfq_close_cooperator(cfqd, cfqq, 0);
+ if (new_cfqq)
+ goto expire;
+
+ /*
* No requests pending. If the active queue still has requests in
* flight or is idling for a new request, allow either of these
* conditions to happen (or time out) before selecting a new queue.
expire:
cfq_slice_expired(cfqd, 0);
new_queue:
- cfqq = cfq_set_active_queue(cfqd);
+ cfqq = cfq_set_active_queue(cfqd, new_cfqq);
keep_queue:
return cfqq;
}
-/*
- * Dispatch some requests from cfqq, moving them to the request queue
- * dispatch list.
- */
-static int
-__cfq_dispatch_requests(struct cfq_data *cfqd, struct cfq_queue *cfqq,
- int max_dispatch)
-{
- int dispatched = 0;
-
- BUG_ON(RB_EMPTY_ROOT(&cfqq->sort_list));
-
- do {
- struct request *rq;
-
- /*
- * follow expired path, else get first next available
- */
- rq = cfq_check_fifo(cfqq);
- if (rq == NULL)
- rq = cfqq->next_rq;
-
- /*
- * finally, insert request into driver dispatch list
- */
- cfq_dispatch_insert(cfqd->queue, rq);
-
- dispatched++;
-
- if (!cfqd->active_cic) {
- atomic_inc(&RQ_CIC(rq)->ioc->refcount);
- cfqd->active_cic = RQ_CIC(rq);
- }
-
- if (RB_EMPTY_ROOT(&cfqq->sort_list))
- break;
-
- } while (dispatched < max_dispatch);
-
- /*
- * expire an async queue immediately if it has used up its slice. idle
- * queue always expire after 1 dispatch round.
- */
- if (cfqd->busy_queues > 1 && ((!cfq_cfqq_sync(cfqq) &&
- dispatched >= cfq_prio_to_maxrq(cfqd, cfqq)) ||
- cfq_class_idle(cfqq))) {
- cfqq->slice_end = jiffies + 1;
- cfq_slice_expired(cfqd, 0);
- }
-
- return dispatched;
-}
-
static int __cfq_forced_dispatch_cfqq(struct cfq_queue *cfqq)
{
int dispatched = 0;
BUG_ON(cfqd->busy_queues);
+ cfq_log(cfqd, "forced_dispatch=%d\n", dispatched);
return dispatched;
}
+/*
+ * Dispatch a request from cfqq, moving them to the request queue
+ * dispatch list.
+ */
+static void cfq_dispatch_request(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+{
+ struct request *rq;
+
+ BUG_ON(RB_EMPTY_ROOT(&cfqq->sort_list));
+
+ /*
+ * follow expired path, else get first next available
+ */
+ rq = cfq_check_fifo(cfqq);
+ if (!rq)
+ rq = cfqq->next_rq;
+
+ /*
+ * insert request into driver dispatch list
+ */
+ cfq_dispatch_insert(cfqd->queue, rq);
+
+ if (!cfqd->active_cic) {
+ struct cfq_io_context *cic = RQ_CIC(rq);
+
+ atomic_inc(&cic->ioc->refcount);
+ cfqd->active_cic = cic;
+ }
+}
+
+/*
+ * Find the cfqq that we need to service and move a request from that to the
+ * dispatch list
+ */
static int cfq_dispatch_requests(struct request_queue *q, int force)
{
struct cfq_data *cfqd = q->elevator->elevator_data;
struct cfq_queue *cfqq;
- int dispatched;
+ unsigned int max_dispatch;
if (!cfqd->busy_queues)
return 0;
if (unlikely(force))
return cfq_forced_dispatch(cfqd);
- dispatched = 0;
- while ((cfqq = cfq_select_queue(cfqd)) != NULL) {
- int max_dispatch;
+ cfqq = cfq_select_queue(cfqd);
+ if (!cfqq)
+ return 0;
- max_dispatch = cfqd->cfq_quantum;
+ /*
+ * If this is an async queue and we have sync IO in flight, let it wait
+ */
+ if (cfqd->sync_flight && !cfq_cfqq_sync(cfqq))
+ return 0;
+
+ max_dispatch = cfqd->cfq_quantum;
+ if (cfq_class_idle(cfqq))
+ max_dispatch = 1;
+
+ /*
+ * Does this cfqq already have too much IO in flight?
+ */
+ if (cfqq->dispatched >= max_dispatch) {
+ /*
+ * idle queue must always only have a single IO in flight
+ */
if (cfq_class_idle(cfqq))
- max_dispatch = 1;
+ return 0;
- if (cfqq->dispatched >= max_dispatch) {
- if (cfqd->busy_queues > 1)
- break;
- if (cfqq->dispatched >= 4 * max_dispatch)
- break;
- }
+ /*
+ * We have other queues, don't allow more IO from this one
+ */
+ if (cfqd->busy_queues > 1)
+ return 0;
- if (cfqd->sync_flight && !cfq_cfqq_sync(cfqq))
- break;
+ /*
+ * we are the only queue, allow up to 4 times of 'quantum'
+ */
+ if (cfqq->dispatched >= 4 * max_dispatch)
+ return 0;
+ }
- cfq_clear_cfqq_must_dispatch(cfqq);
- cfq_clear_cfqq_wait_request(cfqq);
- del_timer(&cfqd->idle_slice_timer);
+ /*
+ * Dispatch a request from this cfqq
+ */
+ cfq_dispatch_request(cfqd, cfqq);
+ cfqq->slice_dispatch++;
+ cfq_clear_cfqq_must_dispatch(cfqq);
- dispatched += __cfq_dispatch_requests(cfqd, cfqq, max_dispatch);
+ /*
+ * expire an async queue immediately if it has used up its slice. idle
+ * queue always expire after 1 dispatch round.
+ */
+ if (cfqd->busy_queues > 1 && ((!cfq_cfqq_sync(cfqq) &&
+ cfqq->slice_dispatch >= cfq_prio_to_maxrq(cfqd, cfqq)) ||
+ cfq_class_idle(cfqq))) {
+ cfqq->slice_end = jiffies + 1;
+ cfq_slice_expired(cfqd, 0);
}
- return dispatched;
+ cfq_log(cfqd, "dispatched a request");
+ return 1;
}
/*
if (!atomic_dec_and_test(&cfqq->ref))
return;
+ cfq_log_cfqq(cfqd, cfqq, "put_queue");
BUG_ON(rb_first(&cfqq->sort_list));
BUG_ON(cfqq->allocated[READ] + cfqq->allocated[WRITE]);
BUG_ON(cfq_cfqq_on_rr(cfqq));
if (ioc->ioc_data == cic)
rcu_assign_pointer(ioc->ioc_data, NULL);
- if (cic->cfqq[ASYNC]) {
- cfq_exit_cfqq(cfqd, cic->cfqq[ASYNC]);
- cic->cfqq[ASYNC] = NULL;
+ if (cic->cfqq[BLK_RW_ASYNC]) {
+ cfq_exit_cfqq(cfqd, cic->cfqq[BLK_RW_ASYNC]);
+ cic->cfqq[BLK_RW_ASYNC] = NULL;
}
- if (cic->cfqq[SYNC]) {
- cfq_exit_cfqq(cfqd, cic->cfqq[SYNC]);
- cic->cfqq[SYNC] = NULL;
+ if (cic->cfqq[BLK_RW_SYNC]) {
+ cfq_exit_cfqq(cfqd, cic->cfqq[BLK_RW_SYNC]);
+ cic->cfqq[BLK_RW_SYNC] = NULL;
}
}
unsigned long flags;
spin_lock_irqsave(q->queue_lock, flags);
- __cfq_exit_single_io_context(cfqd, cic);
+
+ /*
+ * Ensure we get a fresh copy of the ->key to prevent
+ * race between exiting task and queue
+ */
+ smp_read_barrier_depends();
+ if (cic->key)
+ __cfq_exit_single_io_context(cfqd, cic);
+
spin_unlock_irqrestore(q->queue_lock, flags);
}
}
spin_lock_irqsave(cfqd->queue->queue_lock, flags);
- cfqq = cic->cfqq[ASYNC];
+ cfqq = cic->cfqq[BLK_RW_ASYNC];
if (cfqq) {
struct cfq_queue *new_cfqq;
- new_cfqq = cfq_get_queue(cfqd, ASYNC, cic->ioc, GFP_ATOMIC);
+ new_cfqq = cfq_get_queue(cfqd, BLK_RW_ASYNC, cic->ioc,
+ GFP_ATOMIC);
if (new_cfqq) {
- cic->cfqq[ASYNC] = new_cfqq;
+ cic->cfqq[BLK_RW_ASYNC] = new_cfqq;
cfq_put_queue(cfqq);
}
}
- cfqq = cic->cfqq[SYNC];
+ cfqq = cic->cfqq[BLK_RW_SYNC];
if (cfqq)
cfq_mark_cfqq_prio_changed(cfqq);
}
RB_CLEAR_NODE(&cfqq->rb_node);
+ RB_CLEAR_NODE(&cfqq->p_node);
INIT_LIST_HEAD(&cfqq->fifo);
atomic_set(&cfqq->ref, 0);
cfqq->cfqd = cfqd;
cfq_mark_cfqq_prio_changed(cfqq);
- cfq_mark_cfqq_queue_new(cfqq);
cfq_init_prio_data(cfqq, ioc);
cfq_mark_cfqq_idle_window(cfqq);
cfq_mark_cfqq_sync(cfqq);
}
+ cfqq->pid = current->pid;
+ cfq_log_cfqq(cfqd, cfqq, "alloced");
}
if (new_cfqq)
sector_t sdist;
u64 total;
- if (cic->last_request_pos < rq->sector)
+ if (!cic->last_request_pos)
+ sdist = 0;
+ else if (cic->last_request_pos < rq->sector)
sdist = rq->sector - cic->last_request_pos;
else
sdist = cic->last_request_pos - rq->sector;
cfq_update_idle_window(struct cfq_data *cfqd, struct cfq_queue *cfqq,
struct cfq_io_context *cic)
{
- int enable_idle;
+ int old_idle, enable_idle;
/*
* Don't idle for async or idle io prio class
if (!cfq_cfqq_sync(cfqq) || cfq_class_idle(cfqq))
return;
- enable_idle = cfq_cfqq_idle_window(cfqq);
+ enable_idle = old_idle = cfq_cfqq_idle_window(cfqq);
if (!atomic_read(&cic->ioc->nr_tasks) || !cfqd->cfq_slice_idle ||
(cfqd->hw_tag && CIC_SEEKY(cic)))
enable_idle = 1;
}
- if (enable_idle)
- cfq_mark_cfqq_idle_window(cfqq);
- else
- cfq_clear_cfqq_idle_window(cfqq);
+ if (old_idle != enable_idle) {
+ cfq_log_cfqq(cfqd, cfqq, "idle=%d", enable_idle);
+ if (enable_idle)
+ cfq_mark_cfqq_idle_window(cfqq);
+ else
+ cfq_clear_cfqq_idle_window(cfqq);
+ }
}
/*
if (rq_is_meta(rq) && !cfqq->meta_pending)
return 1;
+ /*
+ * Allow an RT request to pre-empt an ongoing non-RT cfqq timeslice.
+ */
+ if (cfq_class_rt(new_cfqq) && !cfq_class_rt(cfqq))
+ return 1;
+
if (!cfqd->active_cic || !cfq_cfqq_wait_request(cfqq))
return 0;
*/
static void cfq_preempt_queue(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
+ cfq_log_cfqq(cfqd, cfqq, "preempt");
cfq_slice_expired(cfqd, 1);
/*
{
struct cfq_io_context *cic = RQ_CIC(rq);
+ cfqd->rq_queued++;
if (rq_is_meta(rq))
cfqq->meta_pending++;
if (cfqq == cfqd->active_queue) {
/*
- * if we are waiting for a request for this queue, let it rip
- * immediately and flag that we must not expire this queue
- * just now
+ * Remember that we saw a request from this process, but
+ * don't start queuing just yet. Otherwise we risk seeing lots
+ * of tiny requests, because we disrupt the normal plugging
+ * and merging. If the request is already larger than a single
+ * page, let it rip immediately. For that case we assume that
+ * merging is already done. Ditto for a busy system that
+ * has other work pending, don't risk delaying until the
+ * idle timer unplug to continue working.
*/
if (cfq_cfqq_wait_request(cfqq)) {
+ if (blk_rq_bytes(rq) > PAGE_CACHE_SIZE ||
+ cfqd->busy_queues > 1) {
+ del_timer(&cfqd->idle_slice_timer);
+ blk_start_queueing(cfqd->queue);
+ }
cfq_mark_cfqq_must_dispatch(cfqq);
- del_timer(&cfqd->idle_slice_timer);
- blk_start_queueing(cfqd->queue);
}
} else if (cfq_should_preempt(cfqd, cfqq, rq)) {
/*
* not the active queue - expire current slice if it is
* idle and has expired it's mean thinktime or this new queue
- * has some old slice time left and is of higher priority
+ * has some old slice time left and is of higher priority or
+ * this new queue is RT and the current one is BE
*/
cfq_preempt_queue(cfqd, cfqq);
- cfq_mark_cfqq_must_dispatch(cfqq);
blk_start_queueing(cfqd->queue);
}
}
struct cfq_data *cfqd = q->elevator->elevator_data;
struct cfq_queue *cfqq = RQ_CFQQ(rq);
+ cfq_log_cfqq(cfqd, cfqq, "insert_request");
cfq_init_prio_data(cfqq, RQ_CIC(rq)->ioc);
cfq_add_rq_rb(rq);
cfq_rq_enqueued(cfqd, cfqq, rq);
}
+/*
+ * Update hw_tag based on peak queue depth over 50 samples under
+ * sufficient load.
+ */
+static void cfq_update_hw_tag(struct cfq_data *cfqd)
+{
+ if (cfqd->rq_in_driver > cfqd->rq_in_driver_peak)
+ cfqd->rq_in_driver_peak = cfqd->rq_in_driver;
+
+ if (cfqd->rq_queued <= CFQ_HW_QUEUE_MIN &&
+ cfqd->rq_in_driver <= CFQ_HW_QUEUE_MIN)
+ return;
+
+ if (cfqd->hw_tag_samples++ < 50)
+ return;
+
+ if (cfqd->rq_in_driver_peak >= CFQ_HW_QUEUE_MIN)
+ cfqd->hw_tag = 1;
+ else
+ cfqd->hw_tag = 0;
+
+ cfqd->hw_tag_samples = 0;
+ cfqd->rq_in_driver_peak = 0;
+}
+
static void cfq_completed_request(struct request_queue *q, struct request *rq)
{
struct cfq_queue *cfqq = RQ_CFQQ(rq);
unsigned long now;
now = jiffies;
+ cfq_log_cfqq(cfqd, cfqq, "complete");
+
+ cfq_update_hw_tag(cfqd);
WARN_ON(!cfqd->rq_in_driver);
WARN_ON(!cfqq->dispatched);
* or if we want to idle in case it has no pending requests.
*/
if (cfqd->active_queue == cfqq) {
+ const bool cfqq_empty = RB_EMPTY_ROOT(&cfqq->sort_list);
+
if (cfq_cfqq_slice_new(cfqq)) {
cfq_set_prio_slice(cfqd, cfqq);
cfq_clear_cfqq_slice_new(cfqq);
}
+ /*
+ * If there are no requests waiting in this queue, and
+ * there are other queues ready to issue requests, AND
+ * those other queues are issuing requests within our
+ * mean seek distance, give them a chance to run instead
+ * of idling.
+ */
if (cfq_slice_used(cfqq) || cfq_class_idle(cfqq))
cfq_slice_expired(cfqd, 1);
- else if (sync && RB_EMPTY_ROOT(&cfqq->sort_list))
+ else if (cfqq_empty && !cfq_close_cooperator(cfqd, cfqq, 1) &&
+ sync && !rq_noidle(rq))
cfq_arm_slice_timer(cfqd);
}
if (!cic)
return ELV_MQUEUE_MAY;
- cfqq = cic_to_cfqq(cic, rw & REQ_RW_SYNC);
+ cfqq = cic_to_cfqq(cic, rw_is_sync(rw));
if (cfqq) {
cfq_init_prio_data(cfqq, cic->ioc);
cfq_prio_boost(cfqq);
cfq_schedule_dispatch(cfqd);
spin_unlock_irqrestore(q->queue_lock, flags);
+ cfq_log(cfqd, "set_request fail");
return 1;
}
struct cfq_data *cfqd =
container_of(work, struct cfq_data, unplug_work);
struct request_queue *q = cfqd->queue;
- unsigned long flags;
- spin_lock_irqsave(q->queue_lock, flags);
+ spin_lock_irq(q->queue_lock);
blk_start_queueing(q);
- spin_unlock_irqrestore(q->queue_lock, flags);
+ spin_unlock_irq(q->queue_lock);
}
/*
unsigned long flags;
int timed_out = 1;
+ cfq_log(cfqd, "idle timer fired");
+
spin_lock_irqsave(cfqd->queue->queue_lock, flags);
cfqq = cfqd->active_queue;
timed_out = 0;
/*
+ * We saw a request before the queue expired, let it through
+ */
+ if (cfq_cfqq_must_dispatch(cfqq))
+ goto out_kick;
+
+ /*
* expired
*/
if (cfq_slice_used(cfqq))
/*
* not expired and it has a request pending, let it dispatch
*/
- if (!RB_EMPTY_ROOT(&cfqq->sort_list)) {
- cfq_mark_cfqq_must_dispatch(cfqq);
+ if (!RB_EMPTY_ROOT(&cfqq->sort_list))
goto out_kick;
- }
}
expire:
cfq_slice_expired(cfqd, timed_out);
static void cfq_shutdown_timer_wq(struct cfq_data *cfqd)
{
del_timer_sync(&cfqd->idle_slice_timer);
- kblockd_flush_work(&cfqd->unplug_work);
+ cancel_work_sync(&cfqd->unplug_work);
}
static void cfq_put_async_queues(struct cfq_data *cfqd)
cfq_put_queue(cfqd->async_idle_cfqq);
}
-static void cfq_exit_queue(elevator_t *e)
+static void cfq_exit_queue(struct elevator_queue *e)
{
struct cfq_data *cfqd = e->elevator_data;
struct request_queue *q = cfqd->queue;
static void *cfq_init_queue(struct request_queue *q)
{
struct cfq_data *cfqd;
+ int i;
cfqd = kmalloc_node(sizeof(*cfqd), GFP_KERNEL | __GFP_ZERO, q->node);
if (!cfqd)
return NULL;
cfqd->service_tree = CFQ_RB_ROOT;
+
+ /*
+ * Not strictly needed (since RB_ROOT just clears the node and we
+ * zeroed cfqd on alloc), but better be safe in case someone decides
+ * to add magic to the rb code
+ */
+ for (i = 0; i < CFQ_PRIO_LISTS; i++)
+ cfqd->prio_trees[i] = RB_ROOT;
+
INIT_LIST_HEAD(&cfqd->cic_list);
cfqd->queue = q;
cfqd->cfq_slice[1] = cfq_slice_sync;
cfqd->cfq_slice_async_rq = cfq_slice_async_rq;
cfqd->cfq_slice_idle = cfq_slice_idle;
+ cfqd->hw_tag = 1;
return cfqd;
}
}
#define SHOW_FUNCTION(__FUNC, __VAR, __CONV) \
-static ssize_t __FUNC(elevator_t *e, char *page) \
+static ssize_t __FUNC(struct elevator_queue *e, char *page) \
{ \
struct cfq_data *cfqd = e->elevator_data; \
unsigned int __data = __VAR; \
#undef SHOW_FUNCTION
#define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV) \
-static ssize_t __FUNC(elevator_t *e, const char *page, size_t count) \
+static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count) \
{ \
struct cfq_data *cfqd = e->elevator_data; \
unsigned int __data; \
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff