static struct kmem_cache *cfq_pool;
static struct kmem_cache *cfq_ioc_pool;
-static DEFINE_PER_CPU(unsigned long, ioc_count);
+static DEFINE_PER_CPU(unsigned long, cfq_ioc_count);
static struct completion *ioc_gone;
static DEFINE_SPINLOCK(ioc_gone_lock);
#define CFQ_RB_ROOT (struct cfq_rb_root) { RB_ROOT, NULL, }
/*
+ * Per process-grouping structure
+ */
+struct cfq_queue {
+ /* reference count */
+ atomic_t ref;
+ /* various state flags, see below */
+ unsigned int flags;
+ /* parent cfq_data */
+ struct cfq_data *cfqd;
+ /* service_tree member */
+ 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 */
+ struct request *next_rq;
+ /* requests queued in sort_list */
+ int queued[2];
+ /* currently allocated requests */
+ int allocated[2];
+ /* fifo list of requests in sort_list */
+ struct list_head fifo;
+
+ unsigned long slice_end;
+ long slice_resid;
+ unsigned int slice_dispatch;
+
+ /* pending metadata requests */
+ int meta_pending;
+ /* number of requests that are on the dispatch list or inside driver */
+ int dispatched;
+
+ /* io prio of this group */
+ unsigned short ioprio, org_ioprio;
+ unsigned short ioprio_class, org_ioprio_class;
+
+ pid_t pid;
+};
+
+/*
* Per block device queue structure
*/
struct cfq_data {
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 rq_in_driver[2];
int sync_flight;
/*
* idle window management
*/
struct timer_list idle_slice_timer;
- struct work_struct unplug_work;
+ struct delayed_work unplug_work;
struct cfq_queue *active_queue;
struct cfq_io_context *active_cic;
struct cfq_queue *async_idle_cfqq;
sector_t last_position;
- unsigned long last_end_request;
/*
* tunables, see top of file
unsigned int cfq_slice[2];
unsigned int cfq_slice_async_rq;
unsigned int cfq_slice_idle;
+ unsigned int cfq_latency;
struct list_head cic_list;
-};
-/*
- * Per process-grouping structure
- */
-struct cfq_queue {
- /* reference count */
- atomic_t ref;
- /* various state flags, see below */
- unsigned int flags;
- /* parent cfq_data */
- struct cfq_data *cfqd;
- /* service_tree member */
- 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 */
- struct request *next_rq;
- /* requests queued in sort_list */
- int queued[2];
- /* currently allocated requests */
- int allocated[2];
- /* fifo list of requests in sort_list */
- struct list_head fifo;
-
- unsigned long slice_end;
- long slice_resid;
- unsigned int slice_dispatch;
-
- /* pending metadata requests */
- int meta_pending;
- /* number of requests that are on the dispatch list or inside driver */
- int dispatched;
-
- /* io prio of this group */
- unsigned short ioprio, org_ioprio;
- unsigned short ioprio_class, org_ioprio_class;
+ /*
+ * Fallback dummy cfqq for extreme OOM conditions
+ */
+ struct cfq_queue oom_cfqq;
- pid_t pid;
+ unsigned long last_end_sync_rq;
};
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_fifo_expire, /* FIFO checked in this slice */
CFQ_CFQQ_FLAG_idle_window, /* slice idling enabled */
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(fifo_expire);
CFQ_CFQQ_FNS(idle_window);
static struct cfq_io_context *cfq_cic_lookup(struct cfq_data *,
struct io_context *);
+static inline int rq_in_driver(struct cfq_data *cfqd)
+{
+ return cfqd->rq_in_driver[0] + cfqd->rq_in_driver[1];
+}
+
static inline struct cfq_queue *cic_to_cfqq(struct cfq_io_context *cic,
int is_sync)
{
*/
static inline int cfq_bio_sync(struct bio *bio)
{
- if (bio_data_dir(bio) == READ || bio_sync(bio))
+ if (bio_data_dir(bio) == READ || bio_rw_flagged(bio, BIO_RW_SYNCIO))
return 1;
return 0;
* scheduler run of queue, if there are requests pending and no one in the
* driver that will restart queueing
*/
-static inline void cfq_schedule_dispatch(struct cfq_data *cfqd)
+static inline void cfq_schedule_dispatch(struct cfq_data *cfqd,
+ unsigned long delay)
{
if (cfqd->busy_queues) {
cfq_log(cfqd, "schedule dispatch");
- kblockd_schedule_work(cfqd->queue, &cfqd->unplug_work);
+ kblockd_schedule_delayed_work(cfqd->queue, &cfqd->unplug_work,
+ delay);
}
}
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);
}
BUG_ON(!cfqd->busy_queues);
cfqd->busy_queues--;
- if (cfq_class_rt(cfqq))
- cfqd->busy_rt_queues--;
}
/*
{
struct cfq_data *cfqd = q->elevator->elevator_data;
- cfqd->rq_in_driver++;
+ cfqd->rq_in_driver[rq_is_sync(rq)]++;
cfq_log_cfqq(cfqd, RQ_CFQQ(rq), "activate rq, drv=%d",
- cfqd->rq_in_driver);
+ rq_in_driver(cfqd));
cfqd->last_position = blk_rq_pos(rq) + blk_rq_sectors(rq);
}
static void cfq_deactivate_request(struct request_queue *q, struct request *rq)
{
struct cfq_data *cfqd = q->elevator->elevator_data;
+ const int sync = rq_is_sync(rq);
- WARN_ON(!cfqd->rq_in_driver);
- cfqd->rq_in_driver--;
+ WARN_ON(!cfqd->rq_in_driver[sync]);
+ cfqd->rq_in_driver[sync]--;
cfq_log_cfqq(cfqd, RQ_CFQQ(rq), "deactivate rq, drv=%d",
- cfqd->rq_in_driver);
+ rq_in_driver(cfqd));
}
static void cfq_remove_request(struct request *rq)
/*
* still requests with the driver, don't idle
*/
- if (cfqd->rq_in_driver)
+ if (rq_in_driver(cfqd))
return;
/*
cfq_log_cfqq(cfqd, cfqq, "dispatch_insert");
+ cfqq->next_rq = cfq_find_next_rq(cfqd, cfqq, rq);
cfq_remove_request(rq);
cfqq->dispatched++;
elv_dispatch_sort(q, rq);
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.
*/
BUG_ON(cfqd->busy_queues);
- cfq_log(cfqd, "forced_dispatch=%d\n", dispatched);
+ cfq_log(cfqd, "forced_dispatch=%d", dispatched);
return dispatched;
}
return 0;
/*
+ * Drain async requests before we start sync IO
+ */
+ if (cfq_cfqq_idle_window(cfqq) && cfqd->rq_in_driver[BLK_RW_ASYNC])
+ return 0;
+
+ /*
* 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;
/*
- * we are the only queue, allow up to 4 times of 'quantum'
+ * Sole queue user, allow bigger slice
*/
- if (cfqq->dispatched >= 4 * max_dispatch)
- return 0;
+ max_dispatch *= 4;
}
/*
+ * Async queues must wait a bit before being allowed dispatch.
+ * We also ramp up the dispatch depth gradually for async IO,
+ * based on the last sync IO we serviced
+ */
+ if (!cfq_cfqq_sync(cfqq) && cfqd->cfq_latency) {
+ unsigned long last_sync = jiffies - cfqd->last_end_sync_rq;
+ unsigned int depth;
+
+ depth = last_sync / cfqd->cfq_slice[1];
+ if (!depth && !cfqq->dispatched)
+ depth = 1;
+ if (depth < max_dispatch)
+ max_dispatch = depth;
+ }
+
+ if (cfqq->dispatched >= max_dispatch)
+ return 0;
+
+ /*
* Dispatch a request from this cfqq
*/
cfq_dispatch_request(cfqd, cfqq);
cfq_slice_expired(cfqd, 0);
}
- cfq_log(cfqd, "dispatched a request");
+ cfq_log_cfqq(cfqd, cfqq, "dispatched a request");
return 1;
}
if (unlikely(cfqd->active_queue == cfqq)) {
__cfq_slice_expired(cfqd, cfqq, 0);
- cfq_schedule_dispatch(cfqd);
+ cfq_schedule_dispatch(cfqd, 0);
}
kmem_cache_free(cfq_pool, cfqq);
cic = container_of(head, struct cfq_io_context, rcu_head);
kmem_cache_free(cfq_ioc_pool, cic);
- elv_ioc_count_dec(ioc_count);
+ elv_ioc_count_dec(cfq_ioc_count);
if (ioc_gone) {
/*
* complete ioc_gone and set it back to NULL
*/
spin_lock(&ioc_gone_lock);
- if (ioc_gone && !elv_ioc_count_read(ioc_count)) {
+ if (ioc_gone && !elv_ioc_count_read(cfq_ioc_count)) {
complete(ioc_gone);
ioc_gone = NULL;
}
{
if (unlikely(cfqq == cfqd->active_queue)) {
__cfq_slice_expired(cfqd, cfqq, 0);
- cfq_schedule_dispatch(cfqd);
+ cfq_schedule_dispatch(cfqd, 0);
}
cfq_put_queue(cfqq);
INIT_HLIST_NODE(&cic->cic_list);
cic->dtor = cfq_free_io_context;
cic->exit = cfq_exit_io_context;
- elv_ioc_count_inc(ioc_count);
+ elv_ioc_count_inc(cfq_ioc_count);
}
return cic;
ioc->ioprio_changed = 0;
}
+static void cfq_init_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq,
+ pid_t pid, int is_sync)
+{
+ 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);
+
+ if (is_sync) {
+ if (!cfq_class_idle(cfqq))
+ cfq_mark_cfqq_idle_window(cfqq);
+ cfq_mark_cfqq_sync(cfqq);
+ }
+ cfqq->pid = pid;
+}
+
static struct cfq_queue *
cfq_find_alloc_queue(struct cfq_data *cfqd, int is_sync,
struct io_context *ioc, gfp_t gfp_mask)
/* cic always exists here */
cfqq = cic_to_cfqq(cic, is_sync);
- if (!cfqq) {
+ /*
+ * Always try a new alloc if we fell back to the OOM cfqq
+ * originally, since it should just be a temporary situation.
+ */
+ if (!cfqq || cfqq == &cfqd->oom_cfqq) {
+ cfqq = NULL;
if (new_cfqq) {
cfqq = new_cfqq;
new_cfqq = NULL;
} else if (gfp_mask & __GFP_WAIT) {
- /*
- * Inform the allocator of the fact that we will
- * just repeat this allocation if it fails, to allow
- * the allocator to do whatever it needs to attempt to
- * free memory.
- */
spin_unlock_irq(cfqd->queue->queue_lock);
new_cfqq = kmem_cache_alloc_node(cfq_pool,
- gfp_mask | __GFP_NOFAIL | __GFP_ZERO,
+ gfp_mask | __GFP_ZERO,
cfqd->queue->node);
spin_lock_irq(cfqd->queue->queue_lock);
- goto retry;
+ if (new_cfqq)
+ goto retry;
} else {
cfqq = kmem_cache_alloc_node(cfq_pool,
gfp_mask | __GFP_ZERO,
cfqd->queue->node);
- if (!cfqq)
- goto out;
}
- 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_init_prio_data(cfqq, ioc);
-
- if (is_sync) {
- if (!cfq_class_idle(cfqq))
- cfq_mark_cfqq_idle_window(cfqq);
- cfq_mark_cfqq_sync(cfqq);
- }
- cfqq->pid = current->pid;
- cfq_log_cfqq(cfqd, cfqq, "alloced");
+ if (cfqq) {
+ cfq_init_cfqq(cfqd, cfqq, current->pid, is_sync);
+ cfq_init_prio_data(cfqq, ioc);
+ cfq_log_cfqq(cfqd, cfqq, "alloced");
+ } else
+ cfqq = &cfqd->oom_cfqq;
}
if (new_cfqq)
kmem_cache_free(cfq_pool, new_cfqq);
-out:
- WARN_ON((gfp_mask & __GFP_WAIT) && !cfqq);
return cfqq;
}
cfqq = *async_cfqq;
}
- if (!cfqq) {
+ if (!cfqq)
cfqq = cfq_find_alloc_queue(cfqd, is_sync, ioc, gfp_mask);
- if (!cfqq)
- return NULL;
- }
/*
* pin the queue now that it's allocated, scheduler exit will prune it
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)))
+ (!cfqd->cfq_latency && cfqd->hw_tag && CIC_SEEKY(cic)))
enable_idle = 0;
else if (sample_valid(cic->ttime_samples)) {
if (cic->ttime_mean > cfqd->cfq_slice_idle)
*/
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 (rq_in_driver(cfqd) > cfqd->rq_in_driver_peak)
+ cfqd->rq_in_driver_peak = rq_in_driver(cfqd);
if (cfqd->rq_queued <= CFQ_HW_QUEUE_MIN &&
- cfqd->rq_in_driver <= CFQ_HW_QUEUE_MIN)
+ rq_in_driver(cfqd) <= CFQ_HW_QUEUE_MIN)
return;
if (cfqd->hw_tag_samples++ < 50)
cfq_update_hw_tag(cfqd);
- WARN_ON(!cfqd->rq_in_driver);
+ WARN_ON(!cfqd->rq_in_driver[sync]);
WARN_ON(!cfqq->dispatched);
- cfqd->rq_in_driver--;
+ cfqd->rq_in_driver[sync]--;
cfqq->dispatched--;
if (cfq_cfqq_sync(cfqq))
cfqd->sync_flight--;
- if (!cfq_class_idle(cfqq))
- cfqd->last_end_request = now;
-
- if (sync)
+ if (sync) {
RQ_CIC(rq)->last_end_request = now;
+ cfqd->last_end_sync_rq = now;
+ }
/*
* If this is the active queue, check if it needs to be expired,
cfq_arm_slice_timer(cfqd);
}
- if (!cfqd->rq_in_driver)
- cfq_schedule_dispatch(cfqd);
+ if (!rq_in_driver(cfqd))
+ cfq_schedule_dispatch(cfqd, 0);
}
/*
static inline int __cfq_may_queue(struct cfq_queue *cfqq)
{
- if ((cfq_cfqq_wait_request(cfqq) || cfq_cfqq_must_alloc(cfqq)) &&
- !cfq_cfqq_must_alloc_slice(cfqq)) {
+ if (cfq_cfqq_wait_request(cfqq) && !cfq_cfqq_must_alloc_slice(cfqq)) {
cfq_mark_cfqq_must_alloc_slice(cfqq);
return ELV_MQUEUE_MUST;
}
goto queue_fail;
cfqq = cic_to_cfqq(cic, is_sync);
- if (!cfqq) {
+ if (!cfqq || cfqq == &cfqd->oom_cfqq) {
cfqq = cfq_get_queue(cfqd, is_sync, cic->ioc, gfp_mask);
-
- if (!cfqq)
- goto queue_fail;
-
cic_set_cfqq(cic, cfqq, is_sync);
}
cfqq->allocated[rw]++;
- cfq_clear_cfqq_must_alloc(cfqq);
atomic_inc(&cfqq->ref);
spin_unlock_irqrestore(q->queue_lock, flags);
if (cic)
put_io_context(cic->ioc);
- cfq_schedule_dispatch(cfqd);
+ cfq_schedule_dispatch(cfqd, 0);
spin_unlock_irqrestore(q->queue_lock, flags);
cfq_log(cfqd, "set_request fail");
return 1;
static void cfq_kick_queue(struct work_struct *work)
{
struct cfq_data *cfqd =
- container_of(work, struct cfq_data, unplug_work);
+ container_of(work, struct cfq_data, unplug_work.work);
struct request_queue *q = cfqd->queue;
spin_lock_irq(q->queue_lock);
expire:
cfq_slice_expired(cfqd, timed_out);
out_kick:
- cfq_schedule_dispatch(cfqd);
+ cfq_schedule_dispatch(cfqd, 0);
out_cont:
spin_unlock_irqrestore(cfqd->queue->queue_lock, flags);
}
static void cfq_shutdown_timer_wq(struct cfq_data *cfqd)
{
del_timer_sync(&cfqd->idle_slice_timer);
- cancel_work_sync(&cfqd->unplug_work);
+ cancel_delayed_work_sync(&cfqd->unplug_work);
}
static void cfq_put_async_queues(struct cfq_data *cfqd)
for (i = 0; i < CFQ_PRIO_LISTS; i++)
cfqd->prio_trees[i] = RB_ROOT;
+ /*
+ * Our fallback cfqq if cfq_find_alloc_queue() runs into OOM issues.
+ * Grab a permanent reference to it, so that the normal code flow
+ * will not attempt to free it.
+ */
+ cfq_init_cfqq(cfqd, &cfqd->oom_cfqq, 1, 0);
+ atomic_inc(&cfqd->oom_cfqq.ref);
+
INIT_LIST_HEAD(&cfqd->cic_list);
cfqd->queue = q;
cfqd->idle_slice_timer.function = cfq_idle_slice_timer;
cfqd->idle_slice_timer.data = (unsigned long) cfqd;
- INIT_WORK(&cfqd->unplug_work, cfq_kick_queue);
+ INIT_DELAYED_WORK(&cfqd->unplug_work, cfq_kick_queue);
- cfqd->last_end_request = jiffies;
cfqd->cfq_quantum = cfq_quantum;
cfqd->cfq_fifo_expire[0] = cfq_fifo_expire[0];
cfqd->cfq_fifo_expire[1] = cfq_fifo_expire[1];
cfqd->cfq_slice[1] = cfq_slice_sync;
cfqd->cfq_slice_async_rq = cfq_slice_async_rq;
cfqd->cfq_slice_idle = cfq_slice_idle;
+ cfqd->cfq_latency = 1;
cfqd->hw_tag = 1;
-
+ cfqd->last_end_sync_rq = jiffies;
return cfqd;
}
SHOW_FUNCTION(cfq_slice_sync_show, cfqd->cfq_slice[1], 1);
SHOW_FUNCTION(cfq_slice_async_show, cfqd->cfq_slice[0], 1);
SHOW_FUNCTION(cfq_slice_async_rq_show, cfqd->cfq_slice_async_rq, 0);
+SHOW_FUNCTION(cfq_low_latency_show, cfqd->cfq_latency, 0);
#undef SHOW_FUNCTION
#define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV) \
STORE_FUNCTION(cfq_slice_async_store, &cfqd->cfq_slice[0], 1, UINT_MAX, 1);
STORE_FUNCTION(cfq_slice_async_rq_store, &cfqd->cfq_slice_async_rq, 1,
UINT_MAX, 0);
+STORE_FUNCTION(cfq_low_latency_store, &cfqd->cfq_latency, 0, 1, 0);
#undef STORE_FUNCTION
#define CFQ_ATTR(name) \
CFQ_ATTR(slice_async),
CFQ_ATTR(slice_async_rq),
CFQ_ATTR(slice_idle),
+ CFQ_ATTR(low_latency),
__ATTR_NULL
};
* this also protects us from entering cfq_slab_kill() with
* pending RCU callbacks
*/
- if (elv_ioc_count_read(ioc_count))
+ if (elv_ioc_count_read(cfq_ioc_count))
wait_for_completion(&all_gone);
cfq_slab_kill();
}