#include <linux/rbtree.h>
#include <linux/ioprio.h>
#include <linux/blktrace_api.h>
-#include "blk-cgroup.h"
+#include "cfq.h"
/*
* tunables
static int cfq_slice_async = HZ / 25;
static const int cfq_slice_async_rq = 2;
static int cfq_slice_idle = HZ / 125;
+static int cfq_group_idle = HZ / 125;
static const int cfq_target_latency = HZ * 3/10; /* 300 ms */
static const int cfq_hist_divisor = 4;
#define RQ_CIC(rq) \
((struct cfq_io_context *) (rq)->elevator_private)
#define RQ_CFQQ(rq) (struct cfq_queue *) ((rq)->elevator_private2)
+#define RQ_CFQG(rq) (struct cfq_group *) ((rq)->elevator_private3)
static struct kmem_cache *cfq_pool;
static struct kmem_cache *cfq_ioc_pool;
static struct completion *ioc_gone;
static DEFINE_SPINLOCK(ioc_gone_lock);
+static DEFINE_SPINLOCK(cic_index_lock);
+static DEFINE_IDA(cic_index_ida);
+
#define CFQ_PRIO_LISTS IOPRIO_BE_NR
#define cfq_class_idle(cfqq) ((cfqq)->ioprio_class == IOPRIO_CLASS_IDLE)
#define cfq_class_rt(cfqq) ((cfqq)->ioprio_class == IOPRIO_CLASS_RT)
unsigned count;
unsigned total_weight;
u64 min_vdisktime;
- struct rb_node *active;
};
#define CFQ_RB_ROOT (struct cfq_rb_root) { .rb = RB_ROOT, .left = NULL, \
.count = 0, .min_vdisktime = 0, }
*/
struct cfq_queue {
/* reference count */
- atomic_t ref;
+ int ref;
/* various state flags, see below */
unsigned int flags;
/* parent cfq_data */
struct cfq_queue *new_cfqq;
struct cfq_group *cfqg;
struct cfq_group *orig_cfqg;
- /* Sectors dispatched in current dispatch round */
+ /* Number of sectors dispatched from queue in single dispatch round */
unsigned long nr_sectors;
};
BE_WORKLOAD = 0,
RT_WORKLOAD = 1,
IDLE_WORKLOAD = 2,
+ CFQ_PRIO_NR,
};
/*
/* group service_tree key */
u64 vdisktime;
unsigned int weight;
- bool on_st;
/* number of cfqq currently on this group */
int nr_cfqq;
- /* Per group busy queus average. Useful for workload slice calc. */
- unsigned int busy_queues_avg[2];
/*
- * rr lists of queues with requests, onle rr for each priority class.
+ * Per group busy queus average. Useful for workload slice calc. We
+ * create the array for each prio class but at run time it is used
+ * only for RT and BE class and slot for IDLE class remains unused.
+ * This is primarily done to avoid confusion and a gcc warning.
+ */
+ unsigned int busy_queues_avg[CFQ_PRIO_NR];
+ /*
+ * rr lists of queues with requests. We maintain service trees for
+ * RT and BE classes. These trees are subdivided in subclasses
+ * of SYNC, SYNC_NOIDLE and ASYNC based on workload type. For IDLE
+ * class there is no subclassification and all the cfq queues go on
+ * a single tree service_tree_idle.
* Counts are embedded in the cfq_rb_root
*/
struct cfq_rb_root service_trees[2][3];
struct blkio_group blkg;
#ifdef CONFIG_CFQ_GROUP_IOSCHED
struct hlist_node cfqd_node;
- atomic_t ref;
+ int ref;
#endif
+ /* number of requests that are on the dispatch list or inside driver */
+ int dispatched;
};
/*
enum wl_type_t serving_type;
unsigned long workload_expires;
struct cfq_group *serving_group;
- bool noidle_tree_requires_idle;
/*
* Each priority tree is sorted by next_request position. These
unsigned int cfq_slice[2];
unsigned int cfq_slice_async_rq;
unsigned int cfq_slice_idle;
+ unsigned int cfq_group_idle;
unsigned int cfq_latency;
unsigned int cfq_group_isolation;
+ unsigned int cic_index;
struct list_head cic_list;
/*
CFQ_CFQQ_FNS(wait_busy);
#undef CFQ_CFQQ_FNS
-#ifdef CONFIG_DEBUG_CFQ_IOSCHED
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
#define cfq_log_cfqq(cfqd, cfqq, fmt, args...) \
blk_add_trace_msg((cfqd)->queue, "cfq%d%c %s " fmt, (cfqq)->pid, \
cfq_cfqq_sync((cfqq)) ? 'S' : 'A', \
&cfqg->service_trees[i][j]: NULL) \
+static inline bool iops_mode(struct cfq_data *cfqd)
+{
+ /*
+ * If we are not idling on queues and it is a NCQ drive, parallel
+ * execution of requests is on and measuring time is not possible
+ * in most of the cases until and unless we drive shallower queue
+ * depths and that becomes a performance bottleneck. In such cases
+ * switch to start providing fairness in terms of number of IOs.
+ */
+ if (!cfqd->cfq_slice_idle && cfqd->hw_tag)
+ return true;
+ else
+ return false;
+}
+
static inline enum wl_prio_t cfqq_prio(struct cfq_queue *cfqq)
{
if (cfq_class_idle(cfqq))
cic->cfqq[is_sync] = cfqq;
}
+#define CIC_DEAD_KEY 1ul
+#define CIC_DEAD_INDEX_SHIFT 1
+
+static inline void *cfqd_dead_key(struct cfq_data *cfqd)
+{
+ return (void *)(cfqd->cic_index << CIC_DEAD_INDEX_SHIFT | CIC_DEAD_KEY);
+}
+
+static inline struct cfq_data *cic_to_cfqd(struct cfq_io_context *cic)
+{
+ struct cfq_data *cfqd = cic->key;
+
+ if (unlikely((unsigned long) cfqd & CIC_DEAD_KEY))
+ return NULL;
+
+ return cfqd;
+}
+
/*
* We regard a request as SYNC, if it's either a read or has the SYNC bit
* set (in which case it could also be direct WRITE).
*/
static inline bool cfq_bio_sync(struct bio *bio)
{
- return bio_data_dir(bio) == READ || bio_rw_flagged(bio, BIO_RW_SYNCIO);
+ return bio_data_dir(bio) == READ || (bio->bi_rw & REQ_SYNC);
}
/*
u64 vdisktime = st->min_vdisktime;
struct cfq_group *cfqg;
- if (st->active) {
- cfqg = rb_entry_cfqg(st->active);
- vdisktime = cfqg->vdisktime;
- }
-
if (st->left) {
cfqg = rb_entry_cfqg(st->left);
vdisktime = min_vdisktime(vdisktime, cfqg->vdisktime);
return cfq_target_latency * cfqg->weight / st->total_weight;
}
-static inline void
-cfq_set_prio_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+static inline unsigned
+cfq_scaled_cfqq_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
unsigned slice = cfq_prio_to_slice(cfqd, cfqq);
if (cfqd->cfq_latency) {
low_slice);
}
}
+ return slice;
+}
+
+static inline void
+cfq_set_prio_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+{
+ unsigned slice = cfq_scaled_cfqq_slice(cfqd, cfqq);
+
cfqq->slice_start = jiffies;
cfqq->slice_end = jiffies + slice;
cfqq->allocated_slice = slice;
static inline bool cfq_slice_used(struct cfq_queue *cfqq)
{
if (cfq_cfqq_slice_new(cfqq))
- return 0;
+ return false;
if (time_before(jiffies, cfqq->slice_end))
- return 0;
+ return false;
- return 1;
+ return true;
}
/*
return rq1;
else if (rq_is_sync(rq2) && !rq_is_sync(rq1))
return rq2;
- if (rq_is_meta(rq1) && !rq_is_meta(rq2))
+ if ((rq1->cmd_flags & REQ_META) && !(rq2->cmd_flags & REQ_META))
return rq1;
- else if (rq_is_meta(rq2) && !rq_is_meta(rq1))
+ else if ((rq2->cmd_flags & REQ_META) &&
+ !(rq1->cmd_flags & REQ_META))
return rq2;
s1 = blk_rq_pos(rq1);
struct rb_node *n;
cfqg->nr_cfqq++;
- if (cfqg->on_st)
+ if (!RB_EMPTY_NODE(&cfqg->rb_node))
return;
/*
cfqg->vdisktime = st->min_vdisktime;
__cfq_group_service_tree_add(st, cfqg);
- cfqg->on_st = true;
st->total_weight += cfqg->weight;
}
{
struct cfq_rb_root *st = &cfqd->grp_service_tree;
- if (st->active == &cfqg->rb_node)
- st->active = NULL;
-
BUG_ON(cfqg->nr_cfqq < 1);
cfqg->nr_cfqq--;
return;
cfq_log_cfqg(cfqd, cfqg, "del_from_rr group");
- cfqg->on_st = false;
st->total_weight -= cfqg->weight;
if (!RB_EMPTY_NODE(&cfqg->rb_node))
cfq_rb_erase(&cfqg->rb_node, st);
cfqg->saved_workload_slice = 0;
- blkiocg_update_blkio_group_dequeue_stats(&cfqg->blkg, 1);
+ cfq_blkiocg_update_dequeue_stats(&cfqg->blkg, 1);
}
static inline unsigned int cfq_cfqq_slice_usage(struct cfq_queue *cfqq)
slice_used = cfqq->allocated_slice;
}
- cfq_log_cfqq(cfqq->cfqd, cfqq, "sl_used=%u sect=%lu", slice_used,
- cfqq->nr_sectors);
return slice_used;
}
struct cfq_queue *cfqq)
{
struct cfq_rb_root *st = &cfqd->grp_service_tree;
- unsigned int used_sl, charge_sl;
+ unsigned int used_sl, charge;
int nr_sync = cfqg->nr_cfqq - cfqg_busy_async_queues(cfqd, cfqg)
- cfqg->service_tree_idle.count;
BUG_ON(nr_sync < 0);
- used_sl = charge_sl = cfq_cfqq_slice_usage(cfqq);
+ used_sl = charge = cfq_cfqq_slice_usage(cfqq);
- if (!cfq_cfqq_sync(cfqq) && !nr_sync)
- charge_sl = cfqq->allocated_slice;
+ if (iops_mode(cfqd))
+ charge = cfqq->slice_dispatch;
+ else if (!cfq_cfqq_sync(cfqq) && !nr_sync)
+ charge = cfqq->allocated_slice;
/* Can't update vdisktime while group is on service tree */
cfq_rb_erase(&cfqg->rb_node, st);
- cfqg->vdisktime += cfq_scale_slice(charge_sl, cfqg);
+ cfqg->vdisktime += cfq_scale_slice(charge, cfqg);
__cfq_group_service_tree_add(st, cfqg);
/* This group is being expired. Save the context */
cfq_log_cfqg(cfqd, cfqg, "served: vt=%llu min_vt=%llu", cfqg->vdisktime,
st->min_vdisktime);
- blkiocg_update_blkio_group_stats(&cfqg->blkg, used_sl,
- cfqq->nr_sectors);
+ cfq_log_cfqq(cfqq->cfqd, cfqq, "sl_used=%u disp=%u charge=%u iops=%u"
+ " sect=%u", used_sl, cfqq->slice_dispatch, charge,
+ iops_mode(cfqd), cfqq->nr_sectors);
+ cfq_blkiocg_update_timeslice_used(&cfqg->blkg, used_sl);
+ cfq_blkiocg_set_start_empty_time(&cfqg->blkg);
}
#ifdef CONFIG_CFQ_GROUP_IOSCHED
return NULL;
}
-void
-cfq_update_blkio_group_weight(struct blkio_group *blkg, unsigned int weight)
+void cfq_update_blkio_group_weight(void *key, struct blkio_group *blkg,
+ unsigned int weight)
{
cfqg_of_blkg(blkg)->weight = weight;
}
if (!cfqg)
goto done;
- cfqg->weight = blkcg->weight;
for_each_cfqg_st(cfqg, i, j, st)
*st = CFQ_RB_ROOT;
RB_CLEAR_NODE(&cfqg->rb_node);
* elevator which will be dropped by either elevator exit
* or cgroup deletion path depending on who is exiting first.
*/
- atomic_set(&cfqg->ref, 1);
+ cfqg->ref = 1;
- /* Add group onto cgroup list */
- sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor);
- blkiocg_add_blkio_group(blkcg, &cfqg->blkg, (void *)cfqd,
+ /*
+ * Add group onto cgroup list. It might happen that bdi->dev is
+ * not initialized yet. Initialize this new group without major
+ * and minor info and this info will be filled in once a new thread
+ * comes for IO. See code above.
+ */
+ if (bdi->dev) {
+ sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor);
+ cfq_blkiocg_add_blkio_group(blkcg, &cfqg->blkg, (void *)cfqd,
MKDEV(major, minor));
+ } else
+ cfq_blkiocg_add_blkio_group(blkcg, &cfqg->blkg, (void *)cfqd,
+ 0);
+
+ cfqg->weight = blkcg_get_weight(blkcg, cfqg->blkg.dev);
/* Add group on cfqd list */
hlist_add_head(&cfqg->cfqd_node, &cfqd->cfqg_list);
return cfqg;
}
+static inline struct cfq_group *cfq_ref_get_cfqg(struct cfq_group *cfqg)
+{
+ cfqg->ref++;
+ return cfqg;
+}
+
static void cfq_link_cfqq_cfqg(struct cfq_queue *cfqq, struct cfq_group *cfqg)
{
/* Currently, all async queues are mapped to root group */
cfqq->cfqg = cfqg;
/* cfqq reference on cfqg */
- atomic_inc(&cfqq->cfqg->ref);
+ cfqq->cfqg->ref++;
}
static void cfq_put_cfqg(struct cfq_group *cfqg)
struct cfq_rb_root *st;
int i, j;
- BUG_ON(atomic_read(&cfqg->ref) <= 0);
- if (!atomic_dec_and_test(&cfqg->ref))
+ BUG_ON(cfqg->ref <= 0);
+ cfqg->ref--;
+ if (cfqg->ref)
return;
for_each_cfqg_st(cfqg, i, j, st)
- BUG_ON(!RB_EMPTY_ROOT(&st->rb) || st->active != NULL);
+ BUG_ON(!RB_EMPTY_ROOT(&st->rb));
kfree(cfqg);
}
* it from cgroup list, then it will take care of destroying
* cfqg also.
*/
- if (!blkiocg_del_blkio_group(&cfqg->blkg))
+ if (!cfq_blkiocg_del_blkio_group(&cfqg->blkg))
cfq_destroy_cfqg(cfqd, cfqg);
}
}
{
return &cfqd->root_group;
}
+
+static inline struct cfq_group *cfq_ref_get_cfqg(struct cfq_group *cfqg)
+{
+ return cfqg;
+}
+
static inline void
cfq_link_cfqq_cfqg(struct cfq_queue *cfqq, struct cfq_group *cfqg) {
cfqq->cfqg = cfqg;
cfq_group_service_tree_del(cfqd, cfqq->cfqg);
cfqq->orig_cfqg = cfqq->cfqg;
cfqq->cfqg = &cfqd->root_group;
- atomic_inc(&cfqd->root_group.ref);
+ cfqd->root_group.ref++;
group_changed = 1;
} else if (!cfqd->cfq_group_isolation
&& cfqq_type(cfqq) == SYNC_WORKLOAD && cfqq->orig_cfqg) {
{
elv_rb_del(&cfqq->sort_list, rq);
cfqq->queued[rq_is_sync(rq)]--;
+ cfq_blkiocg_update_io_remove_stats(&(RQ_CFQG(rq))->blkg,
+ rq_data_dir(rq), rq_is_sync(rq));
cfq_add_rq_rb(rq);
+ cfq_blkiocg_update_io_add_stats(&(RQ_CFQG(rq))->blkg,
+ &cfqq->cfqd->serving_group->blkg, rq_data_dir(rq),
+ rq_is_sync(rq));
}
static struct request *
cfq_del_rq_rb(rq);
cfqq->cfqd->rq_queued--;
- if (rq_is_meta(rq)) {
+ cfq_blkiocg_update_io_remove_stats(&(RQ_CFQG(rq))->blkg,
+ rq_data_dir(rq), rq_is_sync(rq));
+ if (rq->cmd_flags & REQ_META) {
WARN_ON(!cfqq->meta_pending);
cfqq->meta_pending--;
}
}
}
+static void cfq_bio_merged(struct request_queue *q, struct request *req,
+ struct bio *bio)
+{
+ cfq_blkiocg_update_io_merged_stats(&(RQ_CFQG(req))->blkg,
+ bio_data_dir(bio), cfq_bio_sync(bio));
+}
+
static void
cfq_merged_requests(struct request_queue *q, struct request *rq,
struct request *next)
if (cfqq->next_rq == next)
cfqq->next_rq = rq;
cfq_remove_request(next);
+ cfq_blkiocg_update_io_merged_stats(&(RQ_CFQG(rq))->blkg,
+ rq_data_dir(next), rq_is_sync(next));
}
static int cfq_allow_merge(struct request_queue *q, struct request *rq,
return cfqq == RQ_CFQQ(rq);
}
+static inline void cfq_del_timer(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+{
+ del_timer(&cfqd->idle_slice_timer);
+ cfq_blkiocg_update_idle_time_stats(&cfqq->cfqg->blkg);
+}
+
static void __cfq_set_active_queue(struct cfq_data *cfqd,
struct cfq_queue *cfqq)
{
if (cfqq) {
cfq_log_cfqq(cfqd, cfqq, "set_active wl_prio:%d wl_type:%d",
cfqd->serving_prio, cfqd->serving_type);
+ cfq_blkiocg_update_avg_queue_size_stats(&cfqq->cfqg->blkg);
cfqq->slice_start = 0;
cfqq->dispatch_start = jiffies;
cfqq->allocated_slice = 0;
cfq_clear_cfqq_fifo_expire(cfqq);
cfq_mark_cfqq_slice_new(cfqq);
- del_timer(&cfqd->idle_slice_timer);
+ cfq_del_timer(cfqd, cfqq);
}
cfqd->active_queue = cfqq;
cfq_log_cfqq(cfqd, cfqq, "slice expired t=%d", timed_out);
if (cfq_cfqq_wait_request(cfqq))
- del_timer(&cfqd->idle_slice_timer);
+ cfq_del_timer(cfqd, cfqq);
cfq_clear_cfqq_wait_request(cfqq);
cfq_clear_cfqq_wait_busy(cfqq);
/*
* store what was left of this slice, if the queue idled/timed out
*/
- if (timed_out && !cfq_cfqq_slice_new(cfqq)) {
- cfqq->slice_resid = cfqq->slice_end - jiffies;
+ if (timed_out) {
+ if (cfq_cfqq_slice_new(cfqq))
+ cfqq->slice_resid = cfq_scaled_cfqq_slice(cfqd, cfqq);
+ else
+ cfqq->slice_resid = cfqq->slice_end - jiffies;
cfq_log_cfqq(cfqd, cfqq, "resid=%ld", cfqq->slice_resid);
}
if (cfqq == cfqd->active_queue)
cfqd->active_queue = NULL;
- if (&cfqq->cfqg->rb_node == cfqd->grp_service_tree.active)
- cfqd->grp_service_tree.active = NULL;
-
if (cfqd->active_cic) {
put_io_context(cfqd->active_cic->ioc);
cfqd->active_cic = NULL;
BUG_ON(!service_tree);
BUG_ON(!service_tree->count);
+ if (!cfqd->cfq_slice_idle)
+ return false;
+
/* We never do for idle class queues. */
if (prio == IDLE_WORKLOAD)
return false;
* in their service tree.
*/
if (service_tree->count == 1 && cfq_cfqq_sync(cfqq))
- return 1;
+ return true;
cfq_log_cfqq(cfqd, cfqq, "Not idling. st->count:%d",
service_tree->count);
- return 0;
+ return false;
}
static void cfq_arm_slice_timer(struct cfq_data *cfqd)
{
struct cfq_queue *cfqq = cfqd->active_queue;
struct cfq_io_context *cic;
- unsigned long sl;
+ unsigned long sl, group_idle = 0;
/*
* SSD device without seek penalty, disable idling. But only do so
/*
* idle is disabled, either manually or by past process history
*/
- if (!cfqd->cfq_slice_idle || !cfq_should_idle(cfqd, cfqq))
- return;
+ if (!cfq_should_idle(cfqd, cfqq)) {
+ /* no queue idling. Check for group idling */
+ if (cfqd->cfq_group_idle)
+ group_idle = cfqd->cfq_group_idle;
+ else
+ return;
+ }
/*
* still active requests from this queue, don't idle
return;
}
+ /* There are other queues in the group, don't do group idle */
+ if (group_idle && cfqq->cfqg->nr_cfqq > 1)
+ return;
+
cfq_mark_cfqq_wait_request(cfqq);
- sl = cfqd->cfq_slice_idle;
+ if (group_idle)
+ sl = cfqd->cfq_group_idle;
+ else
+ sl = cfqd->cfq_slice_idle;
mod_timer(&cfqd->idle_slice_timer, jiffies + sl);
- cfq_log_cfqq(cfqd, cfqq, "arm_idle: %lu", sl);
+ cfq_blkiocg_update_set_idle_time_stats(&cfqq->cfqg->blkg);
+ cfq_log_cfqq(cfqd, cfqq, "arm_idle: %lu group_idle: %d", sl,
+ group_idle ? 1 : 0);
}
/*
cfqq->next_rq = cfq_find_next_rq(cfqd, cfqq, rq);
cfq_remove_request(rq);
cfqq->dispatched++;
+ (RQ_CFQG(rq))->dispatched++;
elv_dispatch_sort(q, rq);
cfqd->rq_in_flight[cfq_cfqq_sync(cfqq)]++;
cfqq->nr_sectors += blk_rq_sectors(rq);
+ cfq_blkiocg_update_dispatch_stats(&cfqq->cfqg->blkg, blk_rq_bytes(rq),
+ rq_data_dir(rq), rq_is_sync(rq));
}
/*
int process_refs, io_refs;
io_refs = cfqq->allocated[READ] + cfqq->allocated[WRITE];
- process_refs = atomic_read(&cfqq->ref) - io_refs;
+ process_refs = cfqq->ref - io_refs;
BUG_ON(process_refs < 0);
return process_refs;
}
int process_refs, new_process_refs;
struct cfq_queue *__cfqq;
+ /*
+ * If there are no process references on the new_cfqq, then it is
+ * unsafe to follow the ->new_cfqq chain as other cfqq's in the
+ * chain may have dropped their last reference (not just their
+ * last process reference).
+ */
+ if (!cfqq_process_refs(new_cfqq))
+ return;
+
/* Avoid a circular list and skip interim queue merges */
while ((__cfqq = new_cfqq->new_cfqq)) {
if (__cfqq == cfqq)
}
process_refs = cfqq_process_refs(cfqq);
+ new_process_refs = cfqq_process_refs(new_cfqq);
/*
* If the process for the cfqq has gone away, there is no
* sense in merging the queues.
*/
- if (process_refs == 0)
+ if (process_refs == 0 || new_process_refs == 0)
return;
/*
* Merge in the direction of the lesser amount of work.
*/
- new_process_refs = cfqq_process_refs(new_cfqq);
if (new_process_refs >= process_refs) {
cfqq->new_cfqq = new_cfqq;
- atomic_add(process_refs, &new_cfqq->ref);
+ new_cfqq->ref += process_refs;
} else {
new_cfqq->new_cfqq = cfqq;
- atomic_add(new_process_refs, &cfqq->ref);
+ cfqq->ref += new_process_refs;
}
}
unsigned count;
struct cfq_rb_root *st;
unsigned group_slice;
-
- if (!cfqg) {
- cfqd->serving_prio = IDLE_WORKLOAD;
- cfqd->workload_expires = jiffies + 1;
- return;
- }
+ enum wl_prio_t original_prio = cfqd->serving_prio;
/* Choose next priority. RT > BE > IDLE */
if (cfq_group_busy_queues_wl(RT_WORKLOAD, cfqd, cfqg))
return;
}
+ if (original_prio != cfqd->serving_prio)
+ goto new_workload;
+
/*
* For RT and BE, we have to choose also the type
* (SYNC, SYNC_NOIDLE, ASYNC), and to compute a workload
if (count && !time_after(jiffies, cfqd->workload_expires))
return;
+new_workload:
/* otherwise select new workload type */
cfqd->serving_type =
cfq_choose_wl(cfqd, cfqg, cfqd->serving_prio);
slice = max_t(unsigned, slice, CFQ_MIN_TT);
cfq_log(cfqd, "workload slice:%d", slice);
cfqd->workload_expires = jiffies + slice;
- cfqd->noidle_tree_requires_idle = false;
}
static struct cfq_group *cfq_get_next_cfqg(struct cfq_data *cfqd)
if (RB_EMPTY_ROOT(&st->rb))
return NULL;
cfqg = cfq_rb_first_group(st);
- st->active = &cfqg->rb_node;
update_min_vdisktime(st);
return cfqg;
}
cfqq = NULL;
goto keep_queue;
} else
- goto expire;
+ goto check_group_idle;
}
/*
* flight or is idling for a new request, allow either of these
* conditions to happen (or time out) before selecting a new queue.
*/
- if (timer_pending(&cfqd->idle_slice_timer) ||
- (cfqq->dispatched && cfq_should_idle(cfqd, cfqq))) {
+ if (timer_pending(&cfqd->idle_slice_timer)) {
+ cfqq = NULL;
+ goto keep_queue;
+ }
+
+ /*
+ * This is a deep seek queue, but the device is much faster than
+ * the queue can deliver, don't idle
+ **/
+ if (CFQQ_SEEKY(cfqq) && cfq_cfqq_idle_window(cfqq) &&
+ (cfq_cfqq_slice_new(cfqq) ||
+ (cfqq->slice_end - jiffies > jiffies - cfqq->slice_start))) {
+ cfq_clear_cfqq_deep(cfqq);
+ cfq_clear_cfqq_idle_window(cfqq);
+ }
+
+ if (cfqq->dispatched && cfq_should_idle(cfqd, cfqq)) {
+ cfqq = NULL;
+ goto keep_queue;
+ }
+
+ /*
+ * If group idle is enabled and there are requests dispatched from
+ * this group, wait for requests to complete.
+ */
+check_group_idle:
+ if (cfqd->cfq_group_idle && cfqq->cfqg->nr_cfqq == 1
+ && cfqq->cfqg->dispatched) {
cfqq = NULL;
goto keep_queue;
}
{
/* the queue hasn't finished any request, can't estimate */
if (cfq_cfqq_slice_new(cfqq))
- return 1;
+ return true;
if (time_after(jiffies + cfqd->cfq_slice_idle * cfqq->dispatched,
cfqq->slice_end))
- return 1;
+ return true;
- return 0;
+ return false;
}
static bool cfq_may_dispatch(struct cfq_data *cfqd, struct cfq_queue *cfqq)
struct cfq_data *cfqd = cfqq->cfqd;
struct cfq_group *cfqg, *orig_cfqg;
- BUG_ON(atomic_read(&cfqq->ref) <= 0);
+ BUG_ON(cfqq->ref <= 0);
- if (!atomic_dec_and_test(&cfqq->ref))
+ cfqq->ref--;
+ if (cfqq->ref)
return;
cfq_log_cfqq(cfqd, cfqq, "put_queue");
static void cic_free_func(struct io_context *ioc, struct cfq_io_context *cic)
{
unsigned long flags;
+ unsigned long dead_key = (unsigned long) cic->key;
- BUG_ON(!cic->dead_key);
+ BUG_ON(!(dead_key & CIC_DEAD_KEY));
spin_lock_irqsave(&ioc->lock, flags);
- radix_tree_delete(&ioc->radix_root, cic->dead_key);
+ radix_tree_delete(&ioc->radix_root, dead_key >> CIC_DEAD_INDEX_SHIFT);
hlist_del_rcu(&cic->cic_list);
spin_unlock_irqrestore(&ioc->lock, flags);
__call_for_each_cic(ioc, cic_free_func);
}
-static void cfq_exit_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+static void cfq_put_cooperator(struct cfq_queue *cfqq)
{
struct cfq_queue *__cfqq, *next;
- if (unlikely(cfqq == cfqd->active_queue)) {
- __cfq_slice_expired(cfqd, cfqq, 0);
- cfq_schedule_dispatch(cfqd);
- }
-
/*
* If this queue was scheduled to merge with another queue, be
* sure to drop the reference taken on that queue (and others in
cfq_put_queue(__cfqq);
__cfqq = next;
}
+}
+
+static void cfq_exit_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+{
+ if (unlikely(cfqq == cfqd->active_queue)) {
+ __cfq_slice_expired(cfqd, cfqq, 0);
+ cfq_schedule_dispatch(cfqd);
+ }
+
+ cfq_put_cooperator(cfqq);
cfq_put_queue(cfqq);
}
list_del_init(&cic->queue_list);
/*
- * Make sure key == NULL is seen for dead queues
+ * Make sure dead mark is seen for dead queues
*/
smp_wmb();
- cic->dead_key = (unsigned long) cic->key;
- cic->key = NULL;
+ cic->key = cfqd_dead_key(cfqd);
if (ioc->ioc_data == cic)
rcu_assign_pointer(ioc->ioc_data, NULL);
static void cfq_exit_single_io_context(struct io_context *ioc,
struct cfq_io_context *cic)
{
- struct cfq_data *cfqd = cic->key;
+ struct cfq_data *cfqd = cic_to_cfqd(cic);
if (cfqd) {
struct request_queue *q = cfqd->queue;
* race between exiting task and queue
*/
smp_read_barrier_depends();
- if (cic->key)
+ if (cic->key == cfqd)
__cfq_exit_single_io_context(cfqd, cic);
spin_unlock_irqrestore(q->queue_lock, flags);
static void changed_ioprio(struct io_context *ioc, struct cfq_io_context *cic)
{
- struct cfq_data *cfqd = cic->key;
+ struct cfq_data *cfqd = cic_to_cfqd(cic);
struct cfq_queue *cfqq;
unsigned long flags;
RB_CLEAR_NODE(&cfqq->p_node);
INIT_LIST_HEAD(&cfqq->fifo);
- atomic_set(&cfqq->ref, 0);
+ cfqq->ref = 0;
cfqq->cfqd = cfqd;
cfq_mark_cfqq_prio_changed(cfqq);
static void changed_cgroup(struct io_context *ioc, struct cfq_io_context *cic)
{
struct cfq_queue *sync_cfqq = cic_to_cfqq(cic, 1);
- struct cfq_data *cfqd = cic->key;
+ struct cfq_data *cfqd = cic_to_cfqd(cic);
unsigned long flags;
struct request_queue *q;
* pin the queue now that it's allocated, scheduler exit will prune it
*/
if (!is_sync && !(*async_cfqq)) {
- atomic_inc(&cfqq->ref);
+ cfqq->ref++;
*async_cfqq = cfqq;
}
- atomic_inc(&cfqq->ref);
+ cfqq->ref++;
return cfqq;
}
unsigned long flags;
WARN_ON(!list_empty(&cic->queue_list));
+ BUG_ON(cic->key != cfqd_dead_key(cfqd));
spin_lock_irqsave(&ioc->lock, flags);
BUG_ON(ioc->ioc_data == cic);
- radix_tree_delete(&ioc->radix_root, (unsigned long) cfqd);
+ radix_tree_delete(&ioc->radix_root, cfqd->cic_index);
hlist_del_rcu(&cic->cic_list);
spin_unlock_irqrestore(&ioc->lock, flags);
{
struct cfq_io_context *cic;
unsigned long flags;
- void *k;
if (unlikely(!ioc))
return NULL;
}
do {
- cic = radix_tree_lookup(&ioc->radix_root, (unsigned long) cfqd);
+ cic = radix_tree_lookup(&ioc->radix_root, cfqd->cic_index);
rcu_read_unlock();
if (!cic)
break;
- /* ->key must be copied to avoid race with cfq_exit_queue() */
- k = cic->key;
- if (unlikely(!k)) {
+ if (unlikely(cic->key != cfqd)) {
cfq_drop_dead_cic(cfqd, ioc, cic);
rcu_read_lock();
continue;
spin_lock_irqsave(&ioc->lock, flags);
ret = radix_tree_insert(&ioc->radix_root,
- (unsigned long) cfqd, cic);
+ cfqd->cic_index, cic);
if (!ret)
hlist_add_head_rcu(&cic->cic_list, &ioc->cic_list);
spin_unlock_irqrestore(&ioc->lock, flags);
if (cfqq->queued[0] + cfqq->queued[1] >= 4)
cfq_mark_cfqq_deep(cfqq);
- if (!atomic_read(&cic->ioc->nr_tasks) || !cfqd->cfq_slice_idle ||
+ if (cfqq->next_rq && (cfqq->next_rq->cmd_flags & REQ_NOIDLE))
+ enable_idle = 0;
+ else if (!atomic_read(&cic->ioc->nr_tasks) || !cfqd->cfq_slice_idle ||
(!cfq_cfqq_deep(cfqq) && CFQQ_SEEKY(cfqq)))
enable_idle = 0;
else if (sample_valid(cic->ttime_samples)) {
* So both queues are sync. Let the new request get disk time if
* it's a metadata request and the current queue is doing regular IO.
*/
- if (rq_is_meta(rq) && !cfqq->meta_pending)
+ if ((rq->cmd_flags & REQ_META) && !cfqq->meta_pending)
return true;
/*
if (cfq_class_rt(new_cfqq) && !cfq_class_rt(cfqq))
return true;
+ /* An idle queue should not be idle now for some reason */
+ if (RB_EMPTY_ROOT(&cfqq->sort_list) && !cfq_should_idle(cfqd, cfqq))
+ return true;
+
if (!cfqd->active_cic || !cfq_cfqq_wait_request(cfqq))
return false;
*/
static void cfq_preempt_queue(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
+ struct cfq_queue *old_cfqq = cfqd->active_queue;
+
cfq_log_cfqq(cfqd, cfqq, "preempt");
cfq_slice_expired(cfqd, 1);
/*
+ * workload type is changed, don't save slice, otherwise preempt
+ * doesn't happen
+ */
+ if (cfqq_type(old_cfqq) != cfqq_type(cfqq))
+ cfqq->cfqg->saved_workload_slice = 0;
+
+ /*
* Put the new queue at the front of the of the current list,
* so we know that it will be selected next.
*/
struct cfq_io_context *cic = RQ_CIC(rq);
cfqd->rq_queued++;
- if (rq_is_meta(rq))
+ if (rq->cmd_flags & REQ_META)
cfqq->meta_pending++;
cfq_update_io_thinktime(cfqd, cic);
if (cfq_cfqq_wait_request(cfqq)) {
if (blk_rq_bytes(rq) > PAGE_CACHE_SIZE ||
cfqd->busy_queues > 1) {
- del_timer(&cfqd->idle_slice_timer);
+ cfq_del_timer(cfqd, cfqq);
cfq_clear_cfqq_wait_request(cfqq);
- __blk_run_queue(cfqd->queue);
- } else
+ __blk_run_queue(cfqd->queue, false);
+ } else {
+ cfq_blkiocg_update_idle_time_stats(
+ &cfqq->cfqg->blkg);
cfq_mark_cfqq_must_dispatch(cfqq);
+ }
}
} else if (cfq_should_preempt(cfqd, cfqq, rq)) {
/*
* this new queue is RT and the current one is BE
*/
cfq_preempt_queue(cfqd, cfqq);
- __blk_run_queue(cfqd->queue);
+ __blk_run_queue(cfqd->queue, false);
}
}
rq_set_fifo_time(rq, jiffies + cfqd->cfq_fifo_expire[rq_is_sync(rq)]);
list_add_tail(&rq->queuelist, &cfqq->fifo);
cfq_add_rq_rb(rq);
-
+ cfq_blkiocg_update_io_add_stats(&(RQ_CFQG(rq))->blkg,
+ &cfqd->serving_group->blkg, rq_data_dir(rq),
+ rq_is_sync(rq));
cfq_rq_enqueued(cfqd, cfqq, rq);
}
{
struct cfq_io_context *cic = cfqd->active_cic;
+ /* If the queue already has requests, don't wait */
+ if (!RB_EMPTY_ROOT(&cfqq->sort_list))
+ return false;
+
/* If there are other queues in the group, don't wait */
if (cfqq->cfqg->nr_cfqq > 1)
return false;
unsigned long now;
now = jiffies;
- cfq_log_cfqq(cfqd, cfqq, "complete rqnoidle %d", !!rq_noidle(rq));
+ cfq_log_cfqq(cfqd, cfqq, "complete rqnoidle %d",
+ !!(rq->cmd_flags & REQ_NOIDLE));
cfq_update_hw_tag(cfqd);
WARN_ON(!cfqq->dispatched);
cfqd->rq_in_driver--;
cfqq->dispatched--;
+ (RQ_CFQG(rq))->dispatched--;
+ cfq_blkiocg_update_completion_stats(&cfqq->cfqg->blkg,
+ rq_start_time_ns(rq), rq_io_start_time_ns(rq),
+ rq_data_dir(rq), rq_is_sync(rq));
cfqd->rq_in_flight[cfq_cfqq_sync(cfqq)]--;
* the queue.
*/
if (cfq_should_wait_busy(cfqd, cfqq)) {
- cfqq->slice_end = jiffies + cfqd->cfq_slice_idle;
+ unsigned long extend_sl = cfqd->cfq_slice_idle;
+ if (!cfqd->cfq_slice_idle)
+ extend_sl = cfqd->cfq_group_idle;
+ cfqq->slice_end = jiffies + extend_sl;
cfq_mark_cfqq_wait_busy(cfqq);
cfq_log_cfqq(cfqd, cfqq, "will busy wait");
}
cfq_slice_expired(cfqd, 1);
else if (sync && cfqq_empty &&
!cfq_close_cooperator(cfqd, cfqq)) {
- cfqd->noidle_tree_requires_idle |= !rq_noidle(rq);
- /*
- * Idling is enabled for SYNC_WORKLOAD.
- * SYNC_NOIDLE_WORKLOAD idles at the end of the tree
- * only if we processed at least one !rq_noidle request
- */
- if (cfqd->serving_type == SYNC_WORKLOAD
- || cfqd->noidle_tree_requires_idle
- || cfqq->cfqg->nr_cfqq == 1)
- cfq_arm_slice_timer(cfqd);
+ cfq_arm_slice_timer(cfqd);
}
}
rq->elevator_private = NULL;
rq->elevator_private2 = NULL;
+ /* Put down rq reference on cfqg */
+ cfq_put_cfqg(RQ_CFQG(rq));
+ rq->elevator_private3 = NULL;
+
cfq_put_queue(cfqq);
}
}
}
cic_set_cfqq(cic, NULL, 1);
+
+ cfq_put_cooperator(cfqq);
+
cfq_put_queue(cfqq);
return NULL;
}
}
cfqq->allocated[rw]++;
- atomic_inc(&cfqq->ref);
+ cfqq->ref++;
+ rq->elevator_private = cic;
+ rq->elevator_private2 = cfqq;
+ rq->elevator_private3 = cfq_ref_get_cfqg(cfqq->cfqg);
spin_unlock_irqrestore(q->queue_lock, flags);
- rq->elevator_private = cic;
- rq->elevator_private2 = cfqq;
return 0;
queue_fail:
struct request_queue *q = cfqd->queue;
spin_lock_irq(q->queue_lock);
- __blk_run_queue(cfqd->queue);
+ __blk_run_queue(cfqd->queue, false);
spin_unlock_irq(q->queue_lock);
}
cfq_put_async_queues(cfqd);
cfq_release_cfq_groups(cfqd);
- blkiocg_del_blkio_group(&cfqd->root_group.blkg);
+ cfq_blkiocg_del_blkio_group(&cfqd->root_group.blkg);
spin_unlock_irq(q->queue_lock);
cfq_shutdown_timer_wq(cfqd);
+ spin_lock(&cic_index_lock);
+ ida_remove(&cic_index_ida, cfqd->cic_index);
+ spin_unlock(&cic_index_lock);
+
/* Wait for cfqg->blkg->key accessors to exit their grace periods. */
call_rcu(&cfqd->rcu, cfq_cfqd_free);
}
+static int cfq_alloc_cic_index(void)
+{
+ int index, error;
+
+ do {
+ if (!ida_pre_get(&cic_index_ida, GFP_KERNEL))
+ return -ENOMEM;
+
+ spin_lock(&cic_index_lock);
+ error = ida_get_new(&cic_index_ida, &index);
+ spin_unlock(&cic_index_lock);
+ if (error && error != -EAGAIN)
+ return error;
+ } while (error);
+
+ return index;
+}
+
static void *cfq_init_queue(struct request_queue *q)
{
struct cfq_data *cfqd;
struct cfq_group *cfqg;
struct cfq_rb_root *st;
+ i = cfq_alloc_cic_index();
+ if (i < 0)
+ return NULL;
+
cfqd = kmalloc_node(sizeof(*cfqd), GFP_KERNEL | __GFP_ZERO, q->node);
if (!cfqd)
return NULL;
+ /*
+ * Don't need take queue_lock in the routine, since we are
+ * initializing the ioscheduler, and nobody is using cfqd
+ */
+ cfqd->cic_index = i;
+
/* Init root service tree */
cfqd->grp_service_tree = CFQ_RB_ROOT;
* Take a reference to root group which we never drop. This is just
* to make sure that cfq_put_cfqg() does not try to kfree root group
*/
- atomic_set(&cfqg->ref, 1);
- blkiocg_add_blkio_group(&blkio_root_cgroup, &cfqg->blkg, (void *)cfqd,
- 0);
+ cfqg->ref = 1;
+ rcu_read_lock();
+ cfq_blkiocg_add_blkio_group(&blkio_root_cgroup, &cfqg->blkg,
+ (void *)cfqd, 0);
+ rcu_read_unlock();
#endif
/*
* Not strictly needed (since RB_ROOT just clears the node and we
* will not attempt to free it.
*/
cfq_init_cfqq(cfqd, &cfqd->oom_cfqq, 1, 0);
- atomic_inc(&cfqd->oom_cfqq.ref);
+ cfqd->oom_cfqq.ref++;
cfq_link_cfqq_cfqg(&cfqd->oom_cfqq, &cfqd->root_group);
INIT_LIST_HEAD(&cfqd->cic_list);
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_group_idle = cfq_group_idle;
cfqd->cfq_latency = 1;
cfqd->cfq_group_isolation = 0;
cfqd->hw_tag = -1;
* second, in order to have larger depth for async operations.
*/
cfqd->last_delayed_sync = jiffies - HZ;
- INIT_RCU_HEAD(&cfqd->rcu);
return cfqd;
}
SHOW_FUNCTION(cfq_back_seek_max_show, cfqd->cfq_back_max, 0);
SHOW_FUNCTION(cfq_back_seek_penalty_show, cfqd->cfq_back_penalty, 0);
SHOW_FUNCTION(cfq_slice_idle_show, cfqd->cfq_slice_idle, 1);
+SHOW_FUNCTION(cfq_group_idle_show, cfqd->cfq_group_idle, 1);
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);
STORE_FUNCTION(cfq_back_seek_penalty_store, &cfqd->cfq_back_penalty, 1,
UINT_MAX, 0);
STORE_FUNCTION(cfq_slice_idle_store, &cfqd->cfq_slice_idle, 0, UINT_MAX, 1);
+STORE_FUNCTION(cfq_group_idle_store, &cfqd->cfq_group_idle, 0, UINT_MAX, 1);
STORE_FUNCTION(cfq_slice_sync_store, &cfqd->cfq_slice[1], 1, UINT_MAX, 1);
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,
CFQ_ATTR(slice_async),
CFQ_ATTR(slice_async_rq),
CFQ_ATTR(slice_idle),
+ CFQ_ATTR(group_idle),
CFQ_ATTR(low_latency),
CFQ_ATTR(group_isolation),
__ATTR_NULL
.elevator_merged_fn = cfq_merged_request,
.elevator_merge_req_fn = cfq_merged_requests,
.elevator_allow_merge_fn = cfq_allow_merge,
+ .elevator_bio_merged_fn = cfq_bio_merged,
.elevator_dispatch_fn = cfq_dispatch_requests,
.elevator_add_req_fn = cfq_insert_request,
.elevator_activate_req_fn = cfq_activate_request,
.blkio_unlink_group_fn = cfq_unlink_blkio_group,
.blkio_update_group_weight_fn = cfq_update_blkio_group_weight,
},
+ .plid = BLKIO_POLICY_PROP,
};
#else
static struct blkio_policy_type blkio_policy_cfq;
if (!cfq_slice_idle)
cfq_slice_idle = 1;
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
+ if (!cfq_group_idle)
+ cfq_group_idle = 1;
+#else
+ cfq_group_idle = 0;
+#endif
if (cfq_slab_setup())
return -ENOMEM;
*/
if (elv_ioc_count_read(cfq_ioc_count))
wait_for_completion(&all_gone);
+ ida_destroy(&cic_index_ida);
cfq_slab_kill();
}