#include <linux/module.h>
#include <linux/blkdev.h>
#include <linux/elevator.h>
+#include <linux/jiffies.h>
#include <linux/rbtree.h>
#include <linux/ioprio.h>
#include <linux/blktrace_api.h>
+#include "blk-cgroup.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 const int cfq_target_latency = HZ * 3/10; /* 300 ms */
+static const int cfq_hist_divisor = 4;
/*
* offset from end of service tree
*/
#define CFQ_MIN_TT (2)
+/*
+ * Allow merged cfqqs to perform this amount of seeky I/O before
+ * deciding to break the queues up again.
+ */
+#define CFQQ_COOP_TOUT (HZ)
+
#define CFQ_SLICE_SCALE (5)
#define CFQ_HW_QUEUE_MIN (5)
+#define CFQ_SERVICE_SHIFT 12
#define RQ_CIC(rq) \
((struct cfq_io_context *) (rq)->elevator_private)
#define cfq_class_rt(cfqq) ((cfqq)->ioprio_class == IOPRIO_CLASS_RT)
#define sample_valid(samples) ((samples) > 80)
+#define rb_entry_cfqg(node) rb_entry((node), struct cfq_group, rb_node)
/*
* Most of our rbtree usage is for sorting with min extraction, so
struct cfq_rb_root {
struct rb_root rb;
struct rb_node *left;
+ unsigned count;
+ u64 min_vdisktime;
+ struct rb_node *active;
+ unsigned total_weight;
};
-#define CFQ_RB_ROOT (struct cfq_rb_root) { RB_ROOT, NULL, }
+#define CFQ_RB_ROOT (struct cfq_rb_root) { RB_ROOT, NULL, 0, 0, }
/*
* Per process-grouping structure
/* fifo list of requests in sort_list */
struct list_head fifo;
+ /* time when queue got scheduled in to dispatch first request. */
+ unsigned long dispatch_start;
+ /* time when first request from queue completed and slice started. */
+ unsigned long slice_start;
unsigned long slice_end;
long slice_resid;
unsigned int slice_dispatch;
unsigned short ioprio, org_ioprio;
unsigned short ioprio_class, org_ioprio_class;
+ unsigned int seek_samples;
+ u64 seek_total;
+ sector_t seek_mean;
+ sector_t last_request_pos;
+ unsigned long seeky_start;
+
pid_t pid;
+
+ struct cfq_rb_root *service_tree;
+ struct cfq_queue *new_cfqq;
+ struct cfq_group *cfqg;
+};
+
+/*
+ * First index in the service_trees.
+ * IDLE is handled separately, so it has negative index
+ */
+enum wl_prio_t {
+ BE_WORKLOAD = 0,
+ RT_WORKLOAD = 1,
+ IDLE_WORKLOAD = 2,
+};
+
+/*
+ * Second index in the service_trees.
+ */
+enum wl_type_t {
+ ASYNC_WORKLOAD = 0,
+ SYNC_NOIDLE_WORKLOAD = 1,
+ SYNC_WORKLOAD = 2
+};
+
+/* This is per cgroup per device grouping structure */
+struct cfq_group {
+ /* group service_tree member */
+ struct rb_node rb_node;
+
+ /* 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.
+ * Counts are embedded in the cfq_rb_root
+ */
+ struct cfq_rb_root service_trees[2][3];
+ struct cfq_rb_root service_tree_idle;
+
+ unsigned long saved_workload_slice;
+ enum wl_type_t saved_workload;
+ enum wl_prio_t saved_serving_prio;
+ struct blkio_group blkg;
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
+ struct hlist_node cfqd_node;
+#endif
};
/*
*/
struct cfq_data {
struct request_queue *queue;
+ /* Root service tree for cfq_groups */
+ struct cfq_rb_root grp_service_tree;
+ struct cfq_group root_group;
+ /* Number of active cfq groups on group service tree */
+ int nr_groups;
/*
- * rr list of queues with requests and the count of them
+ * The priority currently being served
*/
- struct cfq_rb_root service_tree;
+ enum wl_prio_t serving_prio;
+ 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
*/
int rq_queued;
int hw_tag;
- int hw_tag_samples;
- int rq_in_driver_peak;
+ /*
+ * hw_tag can be
+ * -1 => indeterminate, (cfq will behave as if NCQ is present, to allow better detection)
+ * 1 => NCQ is present (hw_tag_est_depth is the estimated max depth)
+ * 0 => no NCQ
+ */
+ int hw_tag_est_depth;
+ unsigned int hw_tag_samples;
/*
* idle window management
*/
struct timer_list idle_slice_timer;
- struct delayed_work unplug_work;
+ struct work_struct unplug_work;
struct cfq_queue *active_queue;
struct cfq_io_context *active_cic;
struct cfq_queue oom_cfqq;
unsigned long last_end_sync_rq;
+
+ /* List of cfq groups being managed on this device*/
+ struct hlist_head cfqg_list;
};
+static struct cfq_group *cfq_get_next_cfqg(struct cfq_data *cfqd);
+
+static struct cfq_rb_root *service_tree_for(struct cfq_group *cfqg,
+ enum wl_prio_t prio,
+ enum wl_type_t type,
+ struct cfq_data *cfqd)
+{
+ if (!cfqg)
+ return NULL;
+
+ if (prio == IDLE_WORKLOAD)
+ return &cfqg->service_tree_idle;
+
+ return &cfqg->service_trees[prio][type];
+}
+
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_prio_changed, /* task priority has changed */
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 */
+ CFQ_CFQQ_FLAG_coop, /* cfqq is shared */
+ CFQ_CFQQ_FLAG_deep, /* sync cfqq experienced large depth */
};
#define CFQ_CFQQ_FNS(name) \
CFQ_CFQQ_FNS(slice_new);
CFQ_CFQQ_FNS(sync);
CFQ_CFQQ_FNS(coop);
+CFQ_CFQQ_FNS(deep);
#undef CFQ_CFQQ_FNS
#define cfq_log_cfqq(cfqd, cfqq, fmt, args...) \
#define cfq_log(cfqd, fmt, args...) \
blk_add_trace_msg((cfqd)->queue, "cfq " fmt, ##args)
+/* Traverses through cfq group service trees */
+#define for_each_cfqg_st(cfqg, i, j, st) \
+ for (i = 0; i <= IDLE_WORKLOAD; i++) \
+ for (j = 0, st = i < IDLE_WORKLOAD ? &cfqg->service_trees[i][j]\
+ : &cfqg->service_tree_idle; \
+ (i < IDLE_WORKLOAD && j <= SYNC_WORKLOAD) || \
+ (i == IDLE_WORKLOAD && j == 0); \
+ j++, st = i < IDLE_WORKLOAD ? \
+ &cfqg->service_trees[i][j]: NULL) \
+
+
+static inline enum wl_prio_t cfqq_prio(struct cfq_queue *cfqq)
+{
+ if (cfq_class_idle(cfqq))
+ return IDLE_WORKLOAD;
+ if (cfq_class_rt(cfqq))
+ return RT_WORKLOAD;
+ return BE_WORKLOAD;
+}
+
+
+static enum wl_type_t cfqq_type(struct cfq_queue *cfqq)
+{
+ if (!cfq_cfqq_sync(cfqq))
+ return ASYNC_WORKLOAD;
+ if (!cfq_cfqq_idle_window(cfqq))
+ return SYNC_NOIDLE_WORKLOAD;
+ return SYNC_WORKLOAD;
+}
+
+static inline int cfq_group_busy_queues_wl(enum wl_prio_t wl,
+ struct cfq_data *cfqd,
+ struct cfq_group *cfqg)
+{
+ if (wl == IDLE_WORKLOAD)
+ return cfqg->service_tree_idle.count;
+
+ return cfqg->service_trees[wl][ASYNC_WORKLOAD].count
+ + cfqg->service_trees[wl][SYNC_NOIDLE_WORKLOAD].count
+ + cfqg->service_trees[wl][SYNC_WORKLOAD].count;
+}
+
static void cfq_dispatch_insert(struct request_queue *, struct request *);
-static struct cfq_queue *cfq_get_queue(struct cfq_data *, int,
+static struct cfq_queue *cfq_get_queue(struct cfq_data *, bool,
struct io_context *, gfp_t);
static struct cfq_io_context *cfq_cic_lookup(struct cfq_data *,
struct io_context *);
}
static inline struct cfq_queue *cic_to_cfqq(struct cfq_io_context *cic,
- int is_sync)
+ bool is_sync)
{
- return cic->cfqq[!!is_sync];
+ return cic->cfqq[is_sync];
}
static inline void cic_set_cfqq(struct cfq_io_context *cic,
- struct cfq_queue *cfqq, int is_sync)
+ struct cfq_queue *cfqq, bool is_sync)
{
- cic->cfqq[!!is_sync] = cfqq;
+ cic->cfqq[is_sync] = cfqq;
}
/*
* 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 int cfq_bio_sync(struct bio *bio)
+static inline bool cfq_bio_sync(struct bio *bio)
{
- if (bio_data_dir(bio) == READ || bio_rw_flagged(bio, BIO_RW_SYNCIO))
- return 1;
-
- return 0;
+ return bio_data_dir(bio) == READ || bio_rw_flagged(bio, BIO_RW_SYNCIO);
}
/*
* 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,
- unsigned long delay)
+static inline void cfq_schedule_dispatch(struct cfq_data *cfqd)
{
if (cfqd->busy_queues) {
cfq_log(cfqd, "schedule dispatch");
- kblockd_schedule_delayed_work(cfqd->queue, &cfqd->unplug_work,
- delay);
+ kblockd_schedule_work(cfqd->queue, &cfqd->unplug_work);
}
}
{
struct cfq_data *cfqd = q->elevator->elevator_data;
- return !cfqd->busy_queues;
+ return !cfqd->rq_queued;
}
/*
* if a queue is marked sync and has sync io queued. A sync queue with async
* io only, should not get full sync slice length.
*/
-static inline int cfq_prio_slice(struct cfq_data *cfqd, int sync,
+static inline int cfq_prio_slice(struct cfq_data *cfqd, bool sync,
unsigned short prio)
{
const int base_slice = cfqd->cfq_slice[sync];
return cfq_prio_slice(cfqd, cfq_cfqq_sync(cfqq), cfqq->ioprio);
}
+static inline u64 cfq_scale_slice(unsigned long delta, struct cfq_group *cfqg)
+{
+ u64 d = delta << CFQ_SERVICE_SHIFT;
+
+ d = d * BLKIO_WEIGHT_DEFAULT;
+ do_div(d, cfqg->weight);
+ return d;
+}
+
+static inline u64 max_vdisktime(u64 min_vdisktime, u64 vdisktime)
+{
+ s64 delta = (s64)(vdisktime - min_vdisktime);
+ if (delta > 0)
+ min_vdisktime = vdisktime;
+
+ return min_vdisktime;
+}
+
+static inline u64 min_vdisktime(u64 min_vdisktime, u64 vdisktime)
+{
+ s64 delta = (s64)(vdisktime - min_vdisktime);
+ if (delta < 0)
+ min_vdisktime = vdisktime;
+
+ return min_vdisktime;
+}
+
+static void update_min_vdisktime(struct cfq_rb_root *st)
+{
+ 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);
+ }
+
+ st->min_vdisktime = max_vdisktime(st->min_vdisktime, vdisktime);
+}
+
+/*
+ * get averaged number of queues of RT/BE priority.
+ * average is updated, with a formula that gives more weight to higher numbers,
+ * to quickly follows sudden increases and decrease slowly
+ */
+
+static inline unsigned cfq_group_get_avg_queues(struct cfq_data *cfqd,
+ struct cfq_group *cfqg, bool rt)
+{
+ unsigned min_q, max_q;
+ unsigned mult = cfq_hist_divisor - 1;
+ unsigned round = cfq_hist_divisor / 2;
+ unsigned busy = cfq_group_busy_queues_wl(rt, cfqd, cfqg);
+
+ min_q = min(cfqg->busy_queues_avg[rt], busy);
+ max_q = max(cfqg->busy_queues_avg[rt], busy);
+ cfqg->busy_queues_avg[rt] = (mult * max_q + min_q + round) /
+ cfq_hist_divisor;
+ return cfqg->busy_queues_avg[rt];
+}
+
+static inline unsigned
+cfq_group_slice(struct cfq_data *cfqd, struct cfq_group *cfqg)
+{
+ struct cfq_rb_root *st = &cfqd->grp_service_tree;
+
+ return cfq_target_latency * cfqg->weight / st->total_weight;
+}
+
static inline void
cfq_set_prio_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
- cfqq->slice_end = cfq_prio_to_slice(cfqd, cfqq) + jiffies;
+ unsigned slice = cfq_prio_to_slice(cfqd, cfqq);
+ if (cfqd->cfq_latency) {
+ /*
+ * interested queues (we consider only the ones with the same
+ * priority class in the cfq group)
+ */
+ unsigned iq = cfq_group_get_avg_queues(cfqd, cfqq->cfqg,
+ cfq_class_rt(cfqq));
+ unsigned sync_slice = cfqd->cfq_slice[1];
+ unsigned expect_latency = sync_slice * iq;
+ unsigned group_slice = cfq_group_slice(cfqd, cfqq->cfqg);
+
+ if (expect_latency > group_slice) {
+ unsigned base_low_slice = 2 * cfqd->cfq_slice_idle;
+ /* scale low_slice according to IO priority
+ * and sync vs async */
+ unsigned low_slice =
+ min(slice, base_low_slice * slice / sync_slice);
+ /* the adapted slice value is scaled to fit all iqs
+ * into the target latency */
+ slice = max(slice * group_slice / expect_latency,
+ low_slice);
+ }
+ }
+ cfqq->slice_start = jiffies;
+ cfqq->slice_end = jiffies + slice;
cfq_log_cfqq(cfqd, cfqq, "set_slice=%lu", cfqq->slice_end - jiffies);
}
* isn't valid until the first request from the dispatch is activated
* and the slice time set.
*/
-static inline int cfq_slice_used(struct cfq_queue *cfqq)
+static inline bool cfq_slice_used(struct cfq_queue *cfqq)
{
if (cfq_cfqq_slice_new(cfqq))
return 0;
* behind the head is penalized and only allowed to a certain extent.
*/
static struct request *
-cfq_choose_req(struct cfq_data *cfqd, struct request *rq1, struct request *rq2)
+cfq_choose_req(struct cfq_data *cfqd, struct request *rq1, struct request *rq2, sector_t last)
{
- sector_t last, s1, s2, d1 = 0, d2 = 0;
+ sector_t s1, s2, d1 = 0, d2 = 0;
unsigned long back_max;
#define CFQ_RQ1_WRAP 0x01 /* request 1 wraps */
#define CFQ_RQ2_WRAP 0x02 /* request 2 wraps */
s1 = blk_rq_pos(rq1);
s2 = blk_rq_pos(rq2);
- last = cfqd->last_position;
-
/*
* by definition, 1KiB is 2 sectors
*/
*/
static struct cfq_queue *cfq_rb_first(struct cfq_rb_root *root)
{
+ /* Service tree is empty */
+ if (!root->count)
+ return NULL;
+
if (!root->left)
root->left = rb_first(&root->rb);
return NULL;
}
+static struct cfq_group *cfq_rb_first_group(struct cfq_rb_root *root)
+{
+ if (!root->left)
+ root->left = rb_first(&root->rb);
+
+ if (root->left)
+ return rb_entry_cfqg(root->left);
+
+ return NULL;
+}
+
static void rb_erase_init(struct rb_node *n, struct rb_root *root)
{
rb_erase(n, root);
if (root->left == n)
root->left = NULL;
rb_erase_init(n, &root->rb);
+ --root->count;
}
/*
next = rb_entry_rq(rbnext);
}
- return cfq_choose_req(cfqd, next, prev);
+ return cfq_choose_req(cfqd, next, prev, blk_rq_pos(last));
}
static unsigned long cfq_slice_offset(struct cfq_data *cfqd,
/*
* just an approximation, should be ok.
*/
- return (cfqd->busy_queues - 1) * (cfq_prio_slice(cfqd, 1, 0) -
+ return (cfqq->cfqg->nr_cfqq - 1) * (cfq_prio_slice(cfqd, 1, 0) -
cfq_prio_slice(cfqd, cfq_cfqq_sync(cfqq), cfqq->ioprio));
}
+static inline s64
+cfqg_key(struct cfq_rb_root *st, struct cfq_group *cfqg)
+{
+ return cfqg->vdisktime - st->min_vdisktime;
+}
+
+static void
+__cfq_group_service_tree_add(struct cfq_rb_root *st, struct cfq_group *cfqg)
+{
+ struct rb_node **node = &st->rb.rb_node;
+ struct rb_node *parent = NULL;
+ struct cfq_group *__cfqg;
+ s64 key = cfqg_key(st, cfqg);
+ int left = 1;
+
+ while (*node != NULL) {
+ parent = *node;
+ __cfqg = rb_entry_cfqg(parent);
+
+ if (key < cfqg_key(st, __cfqg))
+ node = &parent->rb_left;
+ else {
+ node = &parent->rb_right;
+ left = 0;
+ }
+ }
+
+ if (left)
+ st->left = &cfqg->rb_node;
+
+ rb_link_node(&cfqg->rb_node, parent, node);
+ rb_insert_color(&cfqg->rb_node, &st->rb);
+}
+
+static void
+cfq_group_service_tree_add(struct cfq_data *cfqd, struct cfq_group *cfqg)
+{
+ struct cfq_rb_root *st = &cfqd->grp_service_tree;
+ struct cfq_group *__cfqg;
+ struct rb_node *n;
+
+ cfqg->nr_cfqq++;
+ if (cfqg->on_st)
+ return;
+
+ /*
+ * Currently put the group at the end. Later implement something
+ * so that groups get lesser vtime based on their weights, so that
+ * if group does not loose all if it was not continously backlogged.
+ */
+ n = rb_last(&st->rb);
+ if (n) {
+ __cfqg = rb_entry_cfqg(n);
+ cfqg->vdisktime = __cfqg->vdisktime + CFQ_IDLE_DELAY;
+ } else
+ cfqg->vdisktime = st->min_vdisktime;
+
+ __cfq_group_service_tree_add(st, cfqg);
+ cfqg->on_st = true;
+ cfqd->nr_groups++;
+ st->total_weight += cfqg->weight;
+}
+
+static void
+cfq_group_service_tree_del(struct cfq_data *cfqd, struct cfq_group *cfqg)
+{
+ 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--;
+
+ /* If there are other cfq queues under this group, don't delete it */
+ if (cfqg->nr_cfqq)
+ return;
+
+ cfqg->on_st = false;
+ cfqd->nr_groups--;
+ st->total_weight -= cfqg->weight;
+ if (!RB_EMPTY_NODE(&cfqg->rb_node))
+ cfq_rb_erase(&cfqg->rb_node, st);
+ cfqg->saved_workload_slice = 0;
+}
+
+static inline unsigned int cfq_cfqq_slice_usage(struct cfq_queue *cfqq)
+{
+ unsigned int slice_used, allocated_slice;
+
+ /*
+ * Queue got expired before even a single request completed or
+ * got expired immediately after first request completion.
+ */
+ if (!cfqq->slice_start || cfqq->slice_start == jiffies) {
+ /*
+ * Also charge the seek time incurred to the group, otherwise
+ * if there are mutiple queues in the group, each can dispatch
+ * a single request on seeky media and cause lots of seek time
+ * and group will never know it.
+ */
+ slice_used = max_t(unsigned, (jiffies - cfqq->dispatch_start),
+ 1);
+ } else {
+ slice_used = jiffies - cfqq->slice_start;
+ allocated_slice = cfqq->slice_end - cfqq->slice_start;
+ if (slice_used > allocated_slice)
+ slice_used = allocated_slice;
+ }
+
+ cfq_log_cfqq(cfqq->cfqd, cfqq, "sl_used=%u", slice_used);
+ return slice_used;
+}
+
+static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg,
+ struct cfq_queue *cfqq)
+{
+ struct cfq_rb_root *st = &cfqd->grp_service_tree;
+ unsigned int used_sl;
+
+ used_sl = cfq_cfqq_slice_usage(cfqq);
+
+ /* Can't update vdisktime while group is on service tree */
+ cfq_rb_erase(&cfqg->rb_node, st);
+ cfqg->vdisktime += cfq_scale_slice(used_sl, cfqg);
+ __cfq_group_service_tree_add(st, cfqg);
+
+ /* This group is being expired. Save the context */
+ if (time_after(cfqd->workload_expires, jiffies)) {
+ cfqg->saved_workload_slice = cfqd->workload_expires
+ - jiffies;
+ cfqg->saved_workload = cfqd->serving_type;
+ cfqg->saved_serving_prio = cfqd->serving_prio;
+ } else
+ cfqg->saved_workload_slice = 0;
+}
+
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
+static inline struct cfq_group *cfqg_of_blkg(struct blkio_group *blkg)
+{
+ if (blkg)
+ return container_of(blkg, struct cfq_group, blkg);
+ return NULL;
+}
+
+static struct cfq_group *
+cfq_find_alloc_cfqg(struct cfq_data *cfqd, struct cgroup *cgroup, int create)
+{
+ struct blkio_cgroup *blkcg = cgroup_to_blkio_cgroup(cgroup);
+ struct cfq_group *cfqg = NULL;
+ void *key = cfqd;
+ int i, j;
+ struct cfq_rb_root *st;
+
+ /* Do we need to take this reference */
+ if (!css_tryget(&blkcg->css))
+ return NULL;;
+
+ cfqg = cfqg_of_blkg(blkiocg_lookup_group(blkcg, key));
+ if (cfqg || !create)
+ goto done;
+
+ cfqg = kzalloc_node(sizeof(*cfqg), GFP_ATOMIC, cfqd->queue->node);
+ 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);
+
+ /* Add group onto cgroup list */
+ blkiocg_add_blkio_group(blkcg, &cfqg->blkg, (void *)cfqd);
+
+ /* Add group on cfqd list */
+ hlist_add_head(&cfqg->cfqd_node, &cfqd->cfqg_list);
+
+done:
+ css_put(&blkcg->css);
+ return cfqg;
+}
+
+/*
+ * Search for the cfq group current task belongs to. If create = 1, then also
+ * create the cfq group if it does not exist. request_queue lock must be held.
+ */
+static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd, int create)
+{
+ struct cgroup *cgroup;
+ struct cfq_group *cfqg = NULL;
+
+ rcu_read_lock();
+ cgroup = task_cgroup(current, blkio_subsys_id);
+ cfqg = cfq_find_alloc_cfqg(cfqd, cgroup, create);
+ if (!cfqg && create)
+ cfqg = &cfqd->root_group;
+ rcu_read_unlock();
+ 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 */
+ if (!cfq_cfqq_sync(cfqq))
+ cfqg = &cfqq->cfqd->root_group;
+
+ cfqq->cfqg = cfqg;
+}
+#else /* GROUP_IOSCHED */
+static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd, int create)
+{
+ return &cfqd->root_group;
+}
+static inline void
+cfq_link_cfqq_cfqg(struct cfq_queue *cfqq, struct cfq_group *cfqg) {
+ cfqq->cfqg = cfqg;
+}
+
+#endif /* GROUP_IOSCHED */
+
/*
- * The cfqd->service_tree holds all pending cfq_queue's that have
+ * The cfqd->service_trees holds all pending cfq_queue's that have
* 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)
+ bool add_front)
{
struct rb_node **p, *parent;
struct cfq_queue *__cfqq;
unsigned long rb_key;
+ struct cfq_rb_root *service_tree;
int left;
+ int new_cfqq = 1;
+ service_tree = service_tree_for(cfqq->cfqg, cfqq_prio(cfqq),
+ cfqq_type(cfqq), cfqd);
if (cfq_class_idle(cfqq)) {
rb_key = CFQ_IDLE_DELAY;
- parent = rb_last(&cfqd->service_tree.rb);
+ parent = rb_last(&service_tree->rb);
if (parent && parent != &cfqq->rb_node) {
__cfqq = rb_entry(parent, struct cfq_queue, rb_node);
rb_key += __cfqq->rb_key;
} else
rb_key += jiffies;
} else if (!add_front) {
+ /*
+ * Get our rb key offset. Subtract any residual slice
+ * value carried from last service. A negative resid
+ * count indicates slice overrun, and this should position
+ * the next service time further away in the tree.
+ */
rb_key = cfq_slice_offset(cfqd, cfqq) + jiffies;
- rb_key += cfqq->slice_resid;
+ rb_key -= cfqq->slice_resid;
cfqq->slice_resid = 0;
- } else
- rb_key = 0;
+ } else {
+ rb_key = -HZ;
+ __cfqq = cfq_rb_first(service_tree);
+ rb_key += __cfqq ? __cfqq->rb_key : jiffies;
+ }
if (!RB_EMPTY_NODE(&cfqq->rb_node)) {
+ new_cfqq = 0;
/*
* same position, nothing more to do
*/
- if (rb_key == cfqq->rb_key)
+ if (rb_key == cfqq->rb_key &&
+ cfqq->service_tree == service_tree)
return;
- cfq_rb_erase(&cfqq->rb_node, &cfqd->service_tree);
+ cfq_rb_erase(&cfqq->rb_node, cfqq->service_tree);
+ cfqq->service_tree = NULL;
}
left = 1;
parent = NULL;
- p = &cfqd->service_tree.rb.rb_node;
+ cfqq->service_tree = service_tree;
+ p = &service_tree->rb.rb_node;
while (*p) {
struct rb_node **n;
__cfqq = rb_entry(parent, struct cfq_queue, rb_node);
/*
- * sort RT queues first, we always want to give
- * preference to them. IDLE queues goes to the back.
- * after that, sort on the next service time.
+ * sort by key, that represents service time.
*/
- if (cfq_class_rt(cfqq) > cfq_class_rt(__cfqq))
- n = &(*p)->rb_left;
- else if (cfq_class_rt(cfqq) < cfq_class_rt(__cfqq))
- n = &(*p)->rb_right;
- else if (cfq_class_idle(cfqq) < cfq_class_idle(__cfqq))
- n = &(*p)->rb_left;
- else if (cfq_class_idle(cfqq) > cfq_class_idle(__cfqq))
- n = &(*p)->rb_right;
- else if (rb_key < __cfqq->rb_key)
+ if (time_before(rb_key, __cfqq->rb_key))
n = &(*p)->rb_left;
- else
+ else {
n = &(*p)->rb_right;
-
- if (n == &(*p)->rb_right)
left = 0;
+ }
p = n;
}
if (left)
- cfqd->service_tree.left = &cfqq->rb_node;
+ service_tree->left = &cfqq->rb_node;
cfqq->rb_key = rb_key;
rb_link_node(&cfqq->rb_node, parent, p);
- rb_insert_color(&cfqq->rb_node, &cfqd->service_tree.rb);
+ rb_insert_color(&cfqq->rb_node, &service_tree->rb);
+ service_tree->count++;
+ if (add_front || !new_cfqq)
+ return;
+ cfq_group_service_tree_add(cfqd, cfqq->cfqg);
}
static struct cfq_queue *
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 (!RB_EMPTY_NODE(&cfqq->rb_node)) {
+ cfq_rb_erase(&cfqq->rb_node, cfqq->service_tree);
+ cfqq->service_tree = NULL;
+ }
if (cfqq->p_root) {
rb_erase(&cfqq->p_node, cfqq->p_root);
cfqq->p_root = NULL;
}
+ cfq_group_service_tree_del(cfqd, cfqq->cfqg);
BUG_ON(!cfqd->busy_queues);
cfqd->busy_queues--;
}
static void cfq_del_rq_rb(struct request *rq)
{
struct cfq_queue *cfqq = RQ_CFQQ(rq);
- struct cfq_data *cfqd = cfqq->cfqd;
const int sync = rq_is_sync(rq);
BUG_ON(!cfqq->queued[sync]);
elv_rb_del(&cfqq->sort_list, rq);
- if (cfq_cfqq_on_rr(cfqq) && RB_EMPTY_ROOT(&cfqq->sort_list))
- cfq_del_cfqq_rr(cfqd, cfqq);
+ if (cfq_cfqq_on_rr(cfqq) && RB_EMPTY_ROOT(&cfqq->sort_list)) {
+ /*
+ * Queue will be deleted from service tree when we actually
+ * expire it later. Right now just remove it from prio tree
+ * as it is empty.
+ */
+ if (cfqq->p_root) {
+ rb_erase(&cfqq->p_node, cfqq->p_root);
+ cfqq->p_root = NULL;
+ }
+ }
}
static void cfq_add_rq_rb(struct request *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);
+ cfqq->next_rq = cfq_choose_req(cfqd, cfqq->next_rq, rq, cfqd->last_position);
/*
* adjust priority tree position, if ->next_rq changes
cfq_merged_requests(struct request_queue *q, struct request *rq,
struct request *next)
{
+ struct cfq_queue *cfqq = RQ_CFQQ(rq);
/*
* reposition in fifo if next is older than rq
*/
if (!list_empty(&rq->queuelist) && !list_empty(&next->queuelist) &&
- time_before(next->start_time, rq->start_time))
+ time_before(rq_fifo_time(next), rq_fifo_time(rq))) {
list_move(&rq->queuelist, &next->queuelist);
+ rq_set_fifo_time(rq, rq_fifo_time(next));
+ }
+ if (cfqq->next_rq == next)
+ cfqq->next_rq = rq;
cfq_remove_request(next);
}
* Disallow merge of a sync bio into an async request.
*/
if (cfq_bio_sync(bio) && !rq_is_sync(rq))
- return 0;
+ return false;
/*
* Lookup the cfqq that this bio will be queued with. Allow
*/
cic = cfq_cic_lookup(cfqd, current->io_context);
if (!cic)
- return 0;
+ return false;
cfqq = cic_to_cfqq(cic, cfq_bio_sync(bio));
- if (cfqq == RQ_CFQQ(rq))
- return 1;
-
- return 0;
+ return cfqq == RQ_CFQQ(rq);
}
static void __cfq_set_active_queue(struct cfq_data *cfqd,
{
if (cfqq) {
cfq_log_cfqq(cfqd, cfqq, "set_active");
+ cfqq->slice_start = 0;
+ cfqq->dispatch_start = jiffies;
cfqq->slice_end = 0;
cfqq->slice_dispatch = 0;
*/
static void
__cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq,
- int timed_out)
+ bool timed_out)
{
cfq_log_cfqq(cfqd, cfqq, "slice expired t=%d", timed_out);
cfq_log_cfqq(cfqd, cfqq, "resid=%ld", cfqq->slice_resid);
}
+ cfq_group_served(cfqd, cfqq->cfqg, cfqq);
+
+ if (cfq_cfqq_on_rr(cfqq) && RB_EMPTY_ROOT(&cfqq->sort_list))
+ cfq_del_cfqq_rr(cfqd, cfqq);
+
cfq_resort_rr_list(cfqd, cfqq);
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;
}
}
-static inline void cfq_slice_expired(struct cfq_data *cfqd, int timed_out)
+static inline void cfq_slice_expired(struct cfq_data *cfqd, bool timed_out)
{
struct cfq_queue *cfqq = cfqd->active_queue;
*/
static struct cfq_queue *cfq_get_next_queue(struct cfq_data *cfqd)
{
- if (RB_EMPTY_ROOT(&cfqd->service_tree.rb))
+ struct cfq_rb_root *service_tree =
+ service_tree_for(cfqd->serving_group, cfqd->serving_prio,
+ cfqd->serving_type, cfqd);
+
+ if (!cfqd->rq_queued)
+ return NULL;
+
+ /* There is nothing to dispatch */
+ if (!service_tree)
+ return NULL;
+ if (RB_EMPTY_ROOT(&service_tree->rb))
+ return NULL;
+ return cfq_rb_first(service_tree);
+}
+
+static struct cfq_queue *cfq_get_next_queue_forced(struct cfq_data *cfqd)
+{
+ struct cfq_group *cfqg;
+ struct cfq_queue *cfqq;
+ int i, j;
+ struct cfq_rb_root *st;
+
+ if (!cfqd->rq_queued)
+ return NULL;
+
+ cfqg = cfq_get_next_cfqg(cfqd);
+ if (!cfqg)
return NULL;
- return cfq_rb_first(&cfqd->service_tree);
+ for_each_cfqg_st(cfqg, i, j, st)
+ if ((cfqq = cfq_rb_first(st)) != NULL)
+ return cfqq;
+ return NULL;
}
/*
static struct cfq_queue *cfq_set_active_queue(struct cfq_data *cfqd,
struct cfq_queue *cfqq)
{
- if (!cfqq) {
+ if (!cfqq)
cfqq = cfq_get_next_queue(cfqd);
- if (cfqq)
- cfq_clear_cfqq_coop(cfqq);
- }
__cfq_set_active_queue(cfqd, cfqq);
return cfqq;
return cfqd->last_position - blk_rq_pos(rq);
}
-#define CIC_SEEK_THR 8 * 1024
-#define CIC_SEEKY(cic) ((cic)->seek_mean > CIC_SEEK_THR)
+#define CFQQ_SEEK_THR 8 * 1024
+#define CFQQ_SEEKY(cfqq) ((cfqq)->seek_mean > CFQQ_SEEK_THR)
-static inline int cfq_rq_close(struct cfq_data *cfqd, struct request *rq)
+static inline int cfq_rq_close(struct cfq_data *cfqd, struct cfq_queue *cfqq,
+ struct request *rq)
{
- struct cfq_io_context *cic = cfqd->active_cic;
- sector_t sdist = cic->seek_mean;
+ sector_t sdist = cfqq->seek_mean;
- if (!sample_valid(cic->seek_samples))
- sdist = CIC_SEEK_THR;
+ if (!sample_valid(cfqq->seek_samples))
+ sdist = CFQQ_SEEK_THR;
return cfq_dist_from_last(cfqd, rq) <= sdist;
}
* will contain the closest sector.
*/
__cfqq = rb_entry(parent, struct cfq_queue, p_node);
- if (cfq_rq_close(cfqd, __cfqq->next_rq))
+ if (cfq_rq_close(cfqd, cur_cfqq, __cfqq->next_rq))
return __cfqq;
if (blk_rq_pos(__cfqq->next_rq) < sector)
return NULL;
__cfqq = rb_entry(node, struct cfq_queue, p_node);
- if (cfq_rq_close(cfqd, __cfqq->next_rq))
+ if (cfq_rq_close(cfqd, cur_cfqq, __cfqq->next_rq))
return __cfqq;
return NULL;
* assumption.
*/
static struct cfq_queue *cfq_close_cooperator(struct cfq_data *cfqd,
- struct cfq_queue *cur_cfqq,
- int probe)
+ struct cfq_queue *cur_cfqq)
{
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)
+ if (!cfq_cfqq_sync(cur_cfqq))
+ return NULL;
+ if (CFQQ_SEEKY(cur_cfqq))
return NULL;
/*
if (!cfqq)
return NULL;
- if (cfq_cfqq_coop(cfqq))
+ /*
+ * It only makes sense to merge sync queues.
+ */
+ if (!cfq_cfqq_sync(cfqq))
+ return NULL;
+ if (CFQQ_SEEKY(cfqq))
+ return NULL;
+
+ /*
+ * Do not merge queues of different priority classes
+ */
+ if (cfq_class_rt(cfqq) != cfq_class_rt(cur_cfqq))
return NULL;
- if (!probe)
- cfq_mark_cfqq_coop(cfqq);
return cfqq;
}
+/*
+ * Determine whether we should enforce idle window for this queue.
+ */
+
+static bool cfq_should_idle(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+{
+ enum wl_prio_t prio = cfqq_prio(cfqq);
+ struct cfq_rb_root *service_tree = cfqq->service_tree;
+
+ BUG_ON(!service_tree);
+ BUG_ON(!service_tree->count);
+
+ /* We never do for idle class queues. */
+ if (prio == IDLE_WORKLOAD)
+ return false;
+
+ /* We do for queues that were marked with idle window flag. */
+ if (cfq_cfqq_idle_window(cfqq))
+ return true;
+
+ /*
+ * Otherwise, we do only if they are the last ones
+ * in their service tree.
+ */
+ return service_tree->count == 1;
+}
+
static void cfq_arm_slice_timer(struct cfq_data *cfqd)
{
struct cfq_queue *cfqq = cfqd->active_queue;
/*
* idle is disabled, either manually or by past process history
*/
- if (!cfqd->cfq_slice_idle || !cfq_cfqq_idle_window(cfqq))
+ if (!cfqd->cfq_slice_idle || !cfq_should_idle(cfqd, cfqq))
return;
/*
- * still requests with the driver, don't idle
+ * still active requests from this queue, don't idle
*/
- if (rq_in_driver(cfqd))
+ if (cfqq->dispatched)
return;
/*
if (!cic || !atomic_read(&cic->ioc->nr_tasks))
return;
- cfq_mark_cfqq_wait_request(cfqq);
-
/*
- * we don't want to idle for seeks, but we do want to allow
- * fair distribution of slice time for a process doing back-to-back
- * seeks. so allow a little bit of time for him to submit a new rq
+ * If our average think time is larger than the remaining time
+ * slice, then don't idle. This avoids overrunning the allotted
+ * time slice.
*/
+ if (sample_valid(cic->ttime_samples) &&
+ (cfqq->slice_end - jiffies < cic->ttime_mean))
+ return;
+
+ cfq_mark_cfqq_wait_request(cfqq);
+
sl = cfqd->cfq_slice_idle;
- if (sample_valid(cic->seek_samples) && CIC_SEEKY(cic))
- 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);
*/
static struct request *cfq_check_fifo(struct cfq_queue *cfqq)
{
- struct cfq_data *cfqd = cfqq->cfqd;
- struct request *rq;
- int fifo;
+ struct request *rq = NULL;
if (cfq_cfqq_fifo_expire(cfqq))
return NULL;
if (list_empty(&cfqq->fifo))
return NULL;
- fifo = cfq_cfqq_sync(cfqq);
rq = rq_entry_fifo(cfqq->fifo.next);
-
- if (time_before(jiffies, rq->start_time + cfqd->cfq_fifo_expire[fifo]))
+ if (time_before(jiffies, rq_fifo_time(rq)))
rq = NULL;
- cfq_log_cfqq(cfqd, cfqq, "fifo=%p", rq);
+ cfq_log_cfqq(cfqq->cfqd, cfqq, "fifo=%p", rq);
return rq;
}
return 2 * (base_rq + base_rq * (CFQ_PRIO_LISTS - 1 - cfqq->ioprio));
}
+/*
+ * Must be called with the queue_lock held.
+ */
+static int cfqq_process_refs(struct cfq_queue *cfqq)
+{
+ int process_refs, io_refs;
+
+ io_refs = cfqq->allocated[READ] + cfqq->allocated[WRITE];
+ process_refs = atomic_read(&cfqq->ref) - io_refs;
+ BUG_ON(process_refs < 0);
+ return process_refs;
+}
+
+static void cfq_setup_merge(struct cfq_queue *cfqq, struct cfq_queue *new_cfqq)
+{
+ int process_refs, new_process_refs;
+ struct cfq_queue *__cfqq;
+
+ /* Avoid a circular list and skip interim queue merges */
+ while ((__cfqq = new_cfqq->new_cfqq)) {
+ if (__cfqq == cfqq)
+ return;
+ new_cfqq = __cfqq;
+ }
+
+ process_refs = cfqq_process_refs(cfqq);
+ /*
+ * If the process for the cfqq has gone away, there is no
+ * sense in merging the queues.
+ */
+ if (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);
+ } else {
+ new_cfqq->new_cfqq = cfqq;
+ atomic_add(new_process_refs, &cfqq->ref);
+ }
+}
+
+static enum wl_type_t cfq_choose_wl(struct cfq_data *cfqd,
+ struct cfq_group *cfqg, enum wl_prio_t prio,
+ bool prio_changed)
+{
+ struct cfq_queue *queue;
+ int i;
+ bool key_valid = false;
+ unsigned long lowest_key = 0;
+ enum wl_type_t cur_best = SYNC_NOIDLE_WORKLOAD;
+
+ if (prio_changed) {
+ /*
+ * When priorities switched, we prefer starting
+ * from SYNC_NOIDLE (first choice), or just SYNC
+ * over ASYNC
+ */
+ if (service_tree_for(cfqg, prio, cur_best, cfqd)->count)
+ return cur_best;
+ cur_best = SYNC_WORKLOAD;
+ if (service_tree_for(cfqg, prio, cur_best, cfqd)->count)
+ return cur_best;
+
+ return ASYNC_WORKLOAD;
+ }
+
+ for (i = 0; i < 3; ++i) {
+ /* otherwise, select the one with lowest rb_key */
+ queue = cfq_rb_first(service_tree_for(cfqg, prio, i, cfqd));
+ if (queue &&
+ (!key_valid || time_before(queue->rb_key, lowest_key))) {
+ lowest_key = queue->rb_key;
+ cur_best = i;
+ key_valid = true;
+ }
+ }
+
+ return cur_best;
+}
+
+static void choose_service_tree(struct cfq_data *cfqd, struct cfq_group *cfqg)
+{
+ enum wl_prio_t previous_prio = cfqd->serving_prio;
+ bool prio_changed;
+ unsigned slice;
+ unsigned count;
+ struct cfq_rb_root *st;
+ unsigned group_slice;
+
+ if (!cfqg) {
+ cfqd->serving_prio = IDLE_WORKLOAD;
+ cfqd->workload_expires = jiffies + 1;
+ return;
+ }
+
+ /* Choose next priority. RT > BE > IDLE */
+ if (cfq_group_busy_queues_wl(RT_WORKLOAD, cfqd, cfqg))
+ cfqd->serving_prio = RT_WORKLOAD;
+ else if (cfq_group_busy_queues_wl(BE_WORKLOAD, cfqd, cfqg))
+ cfqd->serving_prio = BE_WORKLOAD;
+ else {
+ cfqd->serving_prio = IDLE_WORKLOAD;
+ cfqd->workload_expires = jiffies + 1;
+ return;
+ }
+
+ /*
+ * For RT and BE, we have to choose also the type
+ * (SYNC, SYNC_NOIDLE, ASYNC), and to compute a workload
+ * expiration time
+ */
+ prio_changed = (cfqd->serving_prio != previous_prio);
+ st = service_tree_for(cfqg, cfqd->serving_prio, cfqd->serving_type,
+ cfqd);
+ count = st->count;
+
+ /*
+ * If priority didn't change, check workload expiration,
+ * and that we still have other queues ready
+ */
+ if (!prio_changed && count &&
+ !time_after(jiffies, cfqd->workload_expires))
+ return;
+
+ /* otherwise select new workload type */
+ cfqd->serving_type =
+ cfq_choose_wl(cfqd, cfqg, cfqd->serving_prio, prio_changed);
+ st = service_tree_for(cfqg, cfqd->serving_prio, cfqd->serving_type,
+ cfqd);
+ count = st->count;
+
+ /*
+ * the workload slice is computed as a fraction of target latency
+ * proportional to the number of queues in that workload, over
+ * all the queues in the same priority class
+ */
+ group_slice = cfq_group_slice(cfqd, cfqg);
+
+ slice = group_slice * count /
+ max_t(unsigned, cfqg->busy_queues_avg[cfqd->serving_prio],
+ cfq_group_busy_queues_wl(cfqd->serving_prio, cfqd, cfqg));
+
+ if (cfqd->serving_type == ASYNC_WORKLOAD)
+ /* async workload slice is scaled down according to
+ * the sync/async slice ratio. */
+ slice = slice * cfqd->cfq_slice[0] / cfqd->cfq_slice[1];
+ else
+ /* sync workload slice is at least 2 * cfq_slice_idle */
+ slice = max(slice, 2 * cfqd->cfq_slice_idle);
+
+ slice = max_t(unsigned, slice, CFQ_MIN_TT);
+ cfqd->workload_expires = jiffies + slice;
+ cfqd->noidle_tree_requires_idle = false;
+}
+
+static struct cfq_group *cfq_get_next_cfqg(struct cfq_data *cfqd)
+{
+ struct cfq_rb_root *st = &cfqd->grp_service_tree;
+ struct cfq_group *cfqg;
+
+ 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;
+}
+
+static void cfq_choose_cfqg(struct cfq_data *cfqd)
+{
+ struct cfq_group *cfqg = cfq_get_next_cfqg(cfqd);
+
+ cfqd->serving_group = cfqg;
+
+ /* Restore the workload type data */
+ if (cfqg->saved_workload_slice) {
+ cfqd->workload_expires = jiffies + cfqg->saved_workload_slice;
+ cfqd->serving_type = cfqg->saved_workload;
+ cfqd->serving_prio = cfqg->saved_serving_prio;
+ }
+ choose_service_tree(cfqd, cfqg);
+}
+
/*
* Select a queue for service. If we have a current active queue,
* check whether to continue servicing it, or retrieve and set a new one.
if (!cfqq)
goto new_queue;
+ if (!cfqd->rq_queued)
+ return NULL;
/*
* The active queue has run out of time, expire it and select new.
*/
* 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.
+ * tree. If possible, merge the expiring queue with the new cfqq.
*/
- new_cfqq = cfq_close_cooperator(cfqd, cfqq, 0);
- if (new_cfqq)
+ new_cfqq = cfq_close_cooperator(cfqd, cfqq);
+ if (new_cfqq) {
+ if (!cfqq->new_cfqq)
+ cfq_setup_merge(cfqq, new_cfqq);
goto expire;
+ }
/*
* No requests pending. If the active queue still has requests in
* conditions to happen (or time out) before selecting a new queue.
*/
if (timer_pending(&cfqd->idle_slice_timer) ||
- (cfqq->dispatched && cfq_cfqq_idle_window(cfqq))) {
+ (cfqq->dispatched && cfq_should_idle(cfqd, cfqq))) {
cfqq = NULL;
goto keep_queue;
}
expire:
cfq_slice_expired(cfqd, 0);
new_queue:
+ /*
+ * Current queue expired. Check if we have to switch to a new
+ * service tree
+ */
+ if (!new_cfqq)
+ cfq_choose_cfqg(cfqd);
+
cfqq = cfq_set_active_queue(cfqd, new_cfqq);
keep_queue:
return cfqq;
}
BUG_ON(!list_empty(&cfqq->fifo));
+
+ /* By default cfqq is not expired if it is empty. Do it explicitly */
+ __cfq_slice_expired(cfqq->cfqd, cfqq, 0);
return dispatched;
}
struct cfq_queue *cfqq;
int dispatched = 0;
- while ((cfqq = cfq_rb_first(&cfqd->service_tree)) != NULL)
+ while ((cfqq = cfq_get_next_queue_forced(cfqd)) != NULL)
dispatched += __cfq_forced_dispatch_cfqq(cfqq);
cfq_slice_expired(cfqd, 0);
-
BUG_ON(cfqd->busy_queues);
cfq_log(cfqd, "forced_dispatch=%d", 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_long_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)
+static bool cfq_may_dispatch(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
- struct cfq_data *cfqd = q->elevator->elevator_data;
- struct cfq_queue *cfqq;
unsigned int max_dispatch;
- if (!cfqd->busy_queues)
- return 0;
-
- if (unlikely(force))
- return cfq_forced_dispatch(cfqd);
-
- cfqq = cfq_select_queue(cfqd);
- if (!cfqq)
- 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 (cfq_should_idle(cfqd, cfqq) && cfqd->rq_in_driver[BLK_RW_ASYNC])
+ return false;
/*
* 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;
+ return false;
max_dispatch = cfqd->cfq_quantum;
if (cfq_class_idle(cfqq))
* idle queue must always only have a single IO in flight
*/
if (cfq_class_idle(cfqq))
- return 0;
+ return false;
/*
* We have other queues, don't allow more IO from this one
*/
if (cfqd->busy_queues > 1)
- return 0;
+ return false;
/*
- * Sole queue user, allow bigger slice
+ * Sole queue user, no limit
*/
- max_dispatch *= 4;
+ max_dispatch = -1;
}
/*
max_dispatch = depth;
}
- if (cfqq->dispatched >= max_dispatch)
+ /*
+ * If we're below the current max, allow a dispatch
+ */
+ return cfqq->dispatched < max_dispatch;
+}
+
+/*
+ * Dispatch a request from cfqq, moving them to the request queue
+ * dispatch list.
+ */
+static bool cfq_dispatch_request(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+{
+ struct request *rq;
+
+ BUG_ON(RB_EMPTY_ROOT(&cfqq->sort_list));
+
+ if (!cfq_may_dispatch(cfqd, cfqq))
+ return false;
+
+ /*
+ * 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_long_inc(&cic->ioc->refcount);
+ cfqd->active_cic = cic;
+ }
+
+ return true;
+}
+
+/*
+ * 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;
+
+ if (!cfqd->busy_queues)
+ return 0;
+
+ if (unlikely(force))
+ return cfq_forced_dispatch(cfqd);
+
+ cfqq = cfq_select_queue(cfqd);
+ if (!cfqq)
return 0;
/*
- * Dispatch a request from this cfqq
+ * Dispatch a request from this cfqq, if it is allowed
*/
- cfq_dispatch_request(cfqd, cfqq);
+ if (!cfq_dispatch_request(cfqd, cfqq))
+ return 0;
+
cfqq->slice_dispatch++;
cfq_clear_cfqq_must_dispatch(cfqq);
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 (unlikely(cfqd->active_queue == cfqq)) {
__cfq_slice_expired(cfqd, cfqq, 0);
- cfq_schedule_dispatch(cfqd, 0);
+ cfq_schedule_dispatch(cfqd);
}
+ BUG_ON(cfq_cfqq_on_rr(cfqq));
kmem_cache_free(cfq_pool, cfqq);
}
static void cfq_exit_cfqq(struct cfq_data *cfqd, 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, 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
+ * the merge chain). See cfq_setup_merge and cfq_merge_cfqqs.
+ */
+ __cfqq = cfqq->new_cfqq;
+ while (__cfqq) {
+ if (__cfqq == cfqq) {
+ WARN(1, "cfqq->new_cfqq loop detected\n");
+ break;
+ }
+ next = __cfqq->new_cfqq;
+ cfq_put_queue(__cfqq);
+ __cfqq = next;
}
cfq_put_queue(cfqq);
}
static void cfq_init_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq,
- pid_t pid, int is_sync)
+ pid_t pid, bool is_sync)
{
RB_CLEAR_NODE(&cfqq->rb_node);
RB_CLEAR_NODE(&cfqq->p_node);
}
static struct cfq_queue *
-cfq_find_alloc_queue(struct cfq_data *cfqd, int is_sync,
+cfq_find_alloc_queue(struct cfq_data *cfqd, bool is_sync,
struct io_context *ioc, gfp_t gfp_mask)
{
struct cfq_queue *cfqq, *new_cfqq = NULL;
struct cfq_io_context *cic;
+ struct cfq_group *cfqg;
retry:
+ cfqg = cfq_get_cfqg(cfqd, 1);
cic = cfq_cic_lookup(cfqd, ioc);
/* cic always exists here */
cfqq = cic_to_cfqq(cic, is_sync);
if (cfqq) {
cfq_init_cfqq(cfqd, cfqq, current->pid, is_sync);
cfq_init_prio_data(cfqq, ioc);
+ cfq_link_cfqq_cfqg(cfqq, cfqg);
cfq_log_cfqq(cfqd, cfqq, "alloced");
} else
cfqq = &cfqd->oom_cfqq;
}
static struct cfq_queue *
-cfq_get_queue(struct cfq_data *cfqd, int is_sync, struct io_context *ioc,
+cfq_get_queue(struct cfq_data *cfqd, bool is_sync, struct io_context *ioc,
gfp_t gfp_mask)
{
const int ioprio = task_ioprio(ioc);
}
static void
-cfq_update_io_seektime(struct cfq_data *cfqd, struct cfq_io_context *cic,
+cfq_update_io_seektime(struct cfq_data *cfqd, struct cfq_queue *cfqq,
struct request *rq)
{
sector_t sdist;
u64 total;
- if (!cic->last_request_pos)
+ if (!cfqq->last_request_pos)
sdist = 0;
- else if (cic->last_request_pos < blk_rq_pos(rq))
- sdist = blk_rq_pos(rq) - cic->last_request_pos;
+ else if (cfqq->last_request_pos < blk_rq_pos(rq))
+ sdist = blk_rq_pos(rq) - cfqq->last_request_pos;
else
- sdist = cic->last_request_pos - blk_rq_pos(rq);
+ sdist = cfqq->last_request_pos - blk_rq_pos(rq);
/*
* Don't allow the seek distance to get too large from the
* odd fragment, pagein, etc
*/
- if (cic->seek_samples <= 60) /* second&third seek */
- sdist = min(sdist, (cic->seek_mean * 4) + 2*1024*1024);
+ if (cfqq->seek_samples <= 60) /* second&third seek */
+ sdist = min(sdist, (cfqq->seek_mean * 4) + 2*1024*1024);
else
- sdist = min(sdist, (cic->seek_mean * 4) + 2*1024*64);
+ sdist = min(sdist, (cfqq->seek_mean * 4) + 2*1024*64);
+
+ cfqq->seek_samples = (7*cfqq->seek_samples + 256) / 8;
+ cfqq->seek_total = (7*cfqq->seek_total + (u64)256*sdist) / 8;
+ total = cfqq->seek_total + (cfqq->seek_samples/2);
+ do_div(total, cfqq->seek_samples);
+ cfqq->seek_mean = (sector_t)total;
- cic->seek_samples = (7*cic->seek_samples + 256) / 8;
- cic->seek_total = (7*cic->seek_total + (u64)256*sdist) / 8;
- total = cic->seek_total + (cic->seek_samples/2);
- do_div(total, cic->seek_samples);
- cic->seek_mean = (sector_t)total;
+ /*
+ * If this cfqq is shared between multiple processes, check to
+ * make sure that those processes are still issuing I/Os within
+ * the mean seek distance. If not, it may be time to break the
+ * queues apart again.
+ */
+ if (cfq_cfqq_coop(cfqq)) {
+ if (CFQQ_SEEKY(cfqq) && !cfqq->seeky_start)
+ cfqq->seeky_start = jiffies;
+ else if (!CFQQ_SEEKY(cfqq))
+ cfqq->seeky_start = 0;
+ }
}
/*
enable_idle = old_idle = cfq_cfqq_idle_window(cfqq);
+ if (cfqq->queued[0] + cfqq->queued[1] >= 4)
+ cfq_mark_cfqq_deep(cfqq);
+
if (!atomic_read(&cic->ioc->nr_tasks) || !cfqd->cfq_slice_idle ||
- (!cfqd->cfq_latency && cfqd->hw_tag && CIC_SEEKY(cic)))
+ (!cfq_cfqq_deep(cfqq) && sample_valid(cfqq->seek_samples)
+ && CFQQ_SEEKY(cfqq)))
enable_idle = 0;
else if (sample_valid(cic->ttime_samples)) {
if (cic->ttime_mean > cfqd->cfq_slice_idle)
* Check if new_cfqq should preempt the currently active queue. Return 0 for
* no or if we aren't sure, a 1 will cause a preempt.
*/
-static int
+static bool
cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
struct request *rq)
{
cfqq = cfqd->active_queue;
if (!cfqq)
- return 0;
+ return false;
if (cfq_slice_used(cfqq))
- return 1;
+ return true;
if (cfq_class_idle(new_cfqq))
- return 0;
+ return false;
if (cfq_class_idle(cfqq))
- return 1;
+ return true;
+
+ /* Allow preemption only if we are idling on sync-noidle tree */
+ if (cfqd->serving_type == SYNC_NOIDLE_WORKLOAD &&
+ cfqq_type(new_cfqq) == SYNC_NOIDLE_WORKLOAD &&
+ new_cfqq->service_tree->count == 2 &&
+ RB_EMPTY_ROOT(&cfqq->sort_list))
+ return true;
/*
* if the new request is sync, but the currently running queue is
* not, let the sync request have priority.
*/
if (rq_is_sync(rq) && !cfq_cfqq_sync(cfqq))
- return 1;
+ return true;
/*
* 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)
- return 1;
+ return true;
/*
* 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;
+ return true;
if (!cfqd->active_cic || !cfq_cfqq_wait_request(cfqq))
- return 0;
+ return false;
/*
* if this request is as-good as one we would expect from the
* current cfqq, let it preempt
*/
- if (cfq_rq_close(cfqd, rq))
- return 1;
+ if (cfq_rq_close(cfqd, cfqq, rq))
+ return true;
- return 0;
+ return false;
}
/*
cfqq->meta_pending++;
cfq_update_io_thinktime(cfqd, cic);
- cfq_update_io_seektime(cfqd, cic, rq);
+ cfq_update_io_seektime(cfqd, cfqq, rq);
cfq_update_idle_window(cfqd, cfqq, cic);
- cic->last_request_pos = blk_rq_pos(rq) + blk_rq_sectors(rq);
+ cfqq->last_request_pos = blk_rq_pos(rq) + blk_rq_sectors(rq);
if (cfqq == cfqd->active_queue) {
/*
if (blk_rq_bytes(rq) > PAGE_CACHE_SIZE ||
cfqd->busy_queues > 1) {
del_timer(&cfqd->idle_slice_timer);
- __blk_run_queue(cfqd->queue);
- }
- cfq_mark_cfqq_must_dispatch(cfqq);
+ __blk_run_queue(cfqd->queue);
+ } else
+ cfq_mark_cfqq_must_dispatch(cfqq);
}
} else if (cfq_should_preempt(cfqd, cfqq, rq)) {
/*
cfq_log_cfqq(cfqd, cfqq, "insert_request");
cfq_init_prio_data(cfqq, RQ_CIC(rq)->ioc);
- cfq_add_rq_rb(rq);
-
+ 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_rq_enqueued(cfqd, cfqq, rq);
}
*/
static void cfq_update_hw_tag(struct cfq_data *cfqd)
{
- if (rq_in_driver(cfqd) > cfqd->rq_in_driver_peak)
- cfqd->rq_in_driver_peak = rq_in_driver(cfqd);
+ struct cfq_queue *cfqq = cfqd->active_queue;
+
+ if (rq_in_driver(cfqd) > cfqd->hw_tag_est_depth)
+ cfqd->hw_tag_est_depth = rq_in_driver(cfqd);
+
+ if (cfqd->hw_tag == 1)
+ return;
if (cfqd->rq_queued <= CFQ_HW_QUEUE_MIN &&
rq_in_driver(cfqd) <= CFQ_HW_QUEUE_MIN)
return;
+ /*
+ * If active queue hasn't enough requests and can idle, cfq might not
+ * dispatch sufficient requests to hardware. Don't zero hw_tag in this
+ * case
+ */
+ if (cfqq && cfq_cfqq_idle_window(cfqq) &&
+ cfqq->dispatched + cfqq->queued[0] + cfqq->queued[1] <
+ CFQ_HW_QUEUE_MIN && rq_in_driver(cfqd) < CFQ_HW_QUEUE_MIN)
+ return;
+
if (cfqd->hw_tag_samples++ < 50)
return;
- if (cfqd->rq_in_driver_peak >= CFQ_HW_QUEUE_MIN)
+ if (cfqd->hw_tag_est_depth >= 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)
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.
+ * Idling is not enabled on:
+ * - expired queues
+ * - idle-priority queues
+ * - async queues
+ * - queues with still some requests queued
+ * - when there is a close cooperator
*/
if (cfq_slice_used(cfqq) || cfq_class_idle(cfqq))
cfq_slice_expired(cfqd, 1);
- else if (cfqq_empty && !cfq_close_cooperator(cfqd, cfqq, 1) &&
- sync && !rq_noidle(rq))
- cfq_arm_slice_timer(cfqd);
+ 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)
+ cfq_arm_slice_timer(cfqd);
+ }
}
if (!rq_in_driver(cfqd))
- cfq_schedule_dispatch(cfqd, 0);
+ cfq_schedule_dispatch(cfqd);
}
/*
cfqq->ioprio = IOPRIO_NORM;
} else {
/*
- * check if we need to unboost the queue
+ * unboost the queue (if needed)
*/
- if (cfqq->ioprio_class != cfqq->org_ioprio_class)
- cfqq->ioprio_class = cfqq->org_ioprio_class;
- if (cfqq->ioprio != cfqq->org_ioprio)
- cfqq->ioprio = cfqq->org_ioprio;
+ cfqq->ioprio_class = cfqq->org_ioprio_class;
+ cfqq->ioprio = cfqq->org_ioprio;
}
}
}
}
+static struct cfq_queue *
+cfq_merge_cfqqs(struct cfq_data *cfqd, struct cfq_io_context *cic,
+ struct cfq_queue *cfqq)
+{
+ cfq_log_cfqq(cfqd, cfqq, "merging with queue %p", cfqq->new_cfqq);
+ cic_set_cfqq(cic, cfqq->new_cfqq, 1);
+ cfq_mark_cfqq_coop(cfqq->new_cfqq);
+ cfq_put_queue(cfqq);
+ return cic_to_cfqq(cic, 1);
+}
+
+static int should_split_cfqq(struct cfq_queue *cfqq)
+{
+ if (cfqq->seeky_start &&
+ time_after(jiffies, cfqq->seeky_start + CFQQ_COOP_TOUT))
+ return 1;
+ return 0;
+}
+
+/*
+ * Returns NULL if a new cfqq should be allocated, or the old cfqq if this
+ * was the last process referring to said cfqq.
+ */
+static struct cfq_queue *
+split_cfqq(struct cfq_io_context *cic, struct cfq_queue *cfqq)
+{
+ if (cfqq_process_refs(cfqq) == 1) {
+ cfqq->seeky_start = 0;
+ cfqq->pid = current->pid;
+ cfq_clear_cfqq_coop(cfqq);
+ return cfqq;
+ }
+
+ cic_set_cfqq(cic, NULL, 1);
+ cfq_put_queue(cfqq);
+ return NULL;
+}
/*
* Allocate cfq data structures associated with this request.
*/
struct cfq_data *cfqd = q->elevator->elevator_data;
struct cfq_io_context *cic;
const int rw = rq_data_dir(rq);
- const int is_sync = rq_is_sync(rq);
+ const bool is_sync = rq_is_sync(rq);
struct cfq_queue *cfqq;
unsigned long flags;
if (!cic)
goto queue_fail;
+new_queue:
cfqq = cic_to_cfqq(cic, is_sync);
if (!cfqq || cfqq == &cfqd->oom_cfqq) {
cfqq = cfq_get_queue(cfqd, is_sync, cic->ioc, gfp_mask);
cic_set_cfqq(cic, cfqq, is_sync);
+ } else {
+ /*
+ * If the queue was seeky for too long, break it apart.
+ */
+ if (cfq_cfqq_coop(cfqq) && should_split_cfqq(cfqq)) {
+ cfq_log_cfqq(cfqd, cfqq, "breaking apart cfqq");
+ cfqq = split_cfqq(cic, cfqq);
+ if (!cfqq)
+ goto new_queue;
+ }
+
+ /*
+ * Check to see if this queue is scheduled to merge with
+ * another, closely cooperating queue. The merging of
+ * queues happens here as it must be done in process context.
+ * The reference on new_cfqq was taken in merge_cfqqs.
+ */
+ if (cfqq->new_cfqq)
+ cfqq = cfq_merge_cfqqs(cfqd, cic, cfqq);
}
cfqq->allocated[rw]++;
if (cic)
put_io_context(cic->ioc);
- cfq_schedule_dispatch(cfqd, 0);
+ cfq_schedule_dispatch(cfqd);
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.work);
+ container_of(work, struct cfq_data, unplug_work);
struct request_queue *q = cfqd->queue;
spin_lock_irq(q->queue_lock);
*/
if (!RB_EMPTY_ROOT(&cfqq->sort_list))
goto out_kick;
+
+ /*
+ * Queue depth flag is reset only when the idle didn't succeed
+ */
+ cfq_clear_cfqq_deep(cfqq);
}
expire:
cfq_slice_expired(cfqd, timed_out);
out_kick:
- cfq_schedule_dispatch(cfqd, 0);
+ cfq_schedule_dispatch(cfqd);
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_delayed_work_sync(&cfqd->unplug_work);
+ cancel_work_sync(&cfqd->unplug_work);
}
static void cfq_put_async_queues(struct cfq_data *cfqd)
static void *cfq_init_queue(struct request_queue *q)
{
struct cfq_data *cfqd;
- int i;
+ int i, j;
+ struct cfq_group *cfqg;
+ struct cfq_rb_root *st;
cfqd = kmalloc_node(sizeof(*cfqd), GFP_KERNEL | __GFP_ZERO, q->node);
if (!cfqd)
return NULL;
- cfqd->service_tree = CFQ_RB_ROOT;
+ /* Init root service tree */
+ cfqd->grp_service_tree = CFQ_RB_ROOT;
+
+ /* Init root group */
+ cfqg = &cfqd->root_group;
+ for_each_cfqg_st(cfqg, i, j, st)
+ *st = CFQ_RB_ROOT;
+ RB_CLEAR_NODE(&cfqg->rb_node);
+
+ /* Give preference to root group over other groups */
+ cfqg->weight = 2*BLKIO_WEIGHT_DEFAULT;
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
+ blkiocg_add_blkio_group(&blkio_root_cgroup, &cfqg->blkg, (void *)cfqd);
+#endif
/*
* Not strictly needed (since RB_ROOT just clears the node and we
* zeroed cfqd on alloc), but better be safe in case someone decides
*/
cfq_init_cfqq(cfqd, &cfqd->oom_cfqq, 1, 0);
atomic_inc(&cfqd->oom_cfqq.ref);
+ cfq_link_cfqq_cfqg(&cfqd->oom_cfqq, &cfqd->root_group);
INIT_LIST_HEAD(&cfqd->cic_list);
cfqd->idle_slice_timer.function = cfq_idle_slice_timer;
cfqd->idle_slice_timer.data = (unsigned long) cfqd;
- INIT_DELAYED_WORK(&cfqd->unplug_work, cfq_kick_queue);
+ INIT_WORK(&cfqd->unplug_work, cfq_kick_queue);
cfqd->cfq_quantum = cfq_quantum;
cfqd->cfq_fifo_expire[0] = cfq_fifo_expire[0];
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->hw_tag = -1;
cfqd->last_end_sync_rq = jiffies;
return cfqd;
}
Code Review / linux-2.6.git / blobdiff