aboutsummaryrefslogtreecommitdiff
path: root/block/cfq-iosched.c
diff options
context:
space:
mode:
Diffstat (limited to 'block/cfq-iosched.c')
-rw-r--r--block/cfq-iosched.c1493
1 files changed, 1338 insertions, 155 deletions
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index aa1e9535e35..cfb0b2f5f63 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -9,9 +9,11 @@
#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
@@ -27,6 +29,8 @@ static const int cfq_slice_sync = HZ / 10;
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
@@ -38,8 +42,15 @@ static int cfq_slice_idle = HZ / 125;
*/
#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)
@@ -57,6 +68,7 @@ static DEFINE_SPINLOCK(ioc_gone_lock);
#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
@@ -67,8 +79,12 @@ static DEFINE_SPINLOCK(ioc_gone_lock);
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
@@ -99,6 +115,11 @@ struct cfq_queue {
/* 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;
+ unsigned int allocated_slice;
+ /* 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;
@@ -112,7 +133,71 @@ struct cfq_queue {
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;
+ struct cfq_group *orig_cfqg;
+ /* Sectors dispatched in current dispatch round */
+ unsigned long nr_sectors;
+};
+
+/*
+ * 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;
+ atomic_t ref;
+#endif
};
/*
@@ -120,11 +205,20 @@ struct cfq_queue {
*/
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
@@ -143,8 +237,14 @@ struct cfq_data {
*/
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
@@ -174,6 +274,7 @@ struct cfq_data {
unsigned int cfq_slice_async_rq;
unsigned int cfq_slice_idle;
unsigned int cfq_latency;
+ unsigned int cfq_group_isolation;
struct list_head cic_list;
@@ -183,8 +284,28 @@ struct cfq_data {
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;
+ struct rcu_head rcu;
};
+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 */
@@ -195,8 +316,10 @@ enum cfqq_state_flags {
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_preempt, /* coop preempt */
+ CFQ_CFQQ_FLAG_coop, /* cfqq is shared */
+ CFQ_CFQQ_FLAG_deep, /* sync cfqq experienced large depth */
+ CFQ_CFQQ_FLAG_wait_busy, /* Waiting for next request */
+ CFQ_CFQQ_FLAG_wait_busy_done, /* Got new request. Expire the queue */
};
#define CFQ_CFQQ_FNS(name) \
@@ -223,14 +346,78 @@ CFQ_CFQQ_FNS(prio_changed);
CFQ_CFQQ_FNS(slice_new);
CFQ_CFQQ_FNS(sync);
CFQ_CFQQ_FNS(coop);
-CFQ_CFQQ_FNS(coop_preempt);
+CFQ_CFQQ_FNS(deep);
+CFQ_CFQQ_FNS(wait_busy);
+CFQ_CFQQ_FNS(wait_busy_done);
#undef CFQ_CFQQ_FNS
+#ifdef CONFIG_DEBUG_CFQ_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', \
+ blkg_path(&(cfqq)->cfqg->blkg), ##args);
+
+#define cfq_log_cfqg(cfqd, cfqg, fmt, args...) \
+ blk_add_trace_msg((cfqd)->queue, "%s " fmt, \
+ blkg_path(&(cfqg)->blkg), ##args); \
+
+#else
#define cfq_log_cfqq(cfqd, cfqq, fmt, args...) \
blk_add_trace_msg((cfqd)->queue, "cfq%d " fmt, (cfqq)->pid, ##args)
+#define cfq_log_cfqg(cfqd, cfqg, fmt, args...) do {} while (0);
+#endif
#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 inline int cfqg_busy_async_queues(struct cfq_data *cfqd,
+ struct cfq_group *cfqg)
+{
+ return cfqg->service_trees[RT_WORKLOAD][ASYNC_WORKLOAD].count
+ + cfqg->service_trees[BE_WORKLOAD][ASYNC_WORKLOAD].count;
+}
+
static void cfq_dispatch_insert(struct request_queue *, struct request *);
static struct cfq_queue *cfq_get_queue(struct cfq_data *, bool,
struct io_context *, gfp_t);
@@ -279,7 +466,7 @@ static int cfq_queue_empty(struct request_queue *q)
{
struct cfq_data *cfqd = q->elevator->elevator_data;
- return !cfqd->busy_queues;
+ return !cfqd->rq_queued;
}
/*
@@ -303,10 +490,110 @@ cfq_prio_to_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
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;
+ cfqq->allocated_slice = slice;
cfq_log_cfqq(cfqd, cfqq, "set_slice=%lu", cfqq->slice_end - jiffies);
}
@@ -331,9 +618,9 @@ static inline bool cfq_slice_used(struct cfq_queue *cfqq)
* 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 */
@@ -356,8 +643,6 @@ cfq_choose_req(struct cfq_data *cfqd, struct request *rq1, struct request *rq2)
s1 = blk_rq_pos(rq1);
s2 = blk_rq_pos(rq2);
- last = cfqd->last_position;
-
/*
* by definition, 1KiB is 2 sectors
*/
@@ -425,6 +710,10 @@ cfq_choose_req(struct cfq_data *cfqd, struct request *rq1, struct request *rq2)
*/
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);
@@ -434,6 +723,17 @@ static struct cfq_queue *cfq_rb_first(struct cfq_rb_root *root)
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);
@@ -445,6 +745,7 @@ static void cfq_rb_erase(struct rb_node *n, struct cfq_rb_root *root)
if (root->left == n)
root->left = NULL;
rb_erase_init(n, &root->rb);
+ --root->count;
}
/*
@@ -471,7 +772,7 @@ cfq_find_next_rq(struct cfq_data *cfqd, struct cfq_queue *cfqq,
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,
@@ -480,12 +781,336 @@ 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;
+
+ cfq_log_cfqg(cfqd, cfqg, "del_from_rr group");
+ 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;
+ blkiocg_update_blkio_group_dequeue_stats(&cfqg->blkg, 1);
+}
+
+static inline unsigned int cfq_cfqq_slice_usage(struct cfq_queue *cfqq)
+{
+ unsigned int slice_used;
+
+ /*
+ * 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;
+ if (slice_used > cfqq->allocated_slice)
+ slice_used = cfqq->allocated_slice;
+ }
+
+ cfq_log_cfqq(cfqq->cfqd, cfqq, "sl_used=%u sect=%lu", slice_used,
+ cfqq->nr_sectors);
+ 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, charge_sl;
+ 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);
+
+ if (!cfq_cfqq_sync(cfqq) && !nr_sync)
+ charge_sl = 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);
+ __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;
+
+ 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);
+}
+
+#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;
+}
+
+void
+cfq_update_blkio_group_weight(struct blkio_group *blkg, unsigned int weight)
+{
+ cfqg_of_blkg(blkg)->weight = weight;
+}
+
+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;
+ struct backing_dev_info *bdi = &cfqd->queue->backing_dev_info;
+ unsigned int major, minor;
+
+ /* Do we need to take this reference */
+ if (!blkiocg_css_tryget(blkcg))
+ 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);
+
+ /*
+ * Take the initial reference that will be released on destroy
+ * This can be thought of a joint reference by cgroup and
+ * elevator which will be dropped by either elevator exit
+ * or cgroup deletion path depending on who is exiting first.
+ */
+ atomic_set(&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,
+ MKDEV(major, minor));
+
+ /* Add group on cfqd list */
+ hlist_add_head(&cfqg->cfqd_node, &cfqd->cfqg_list);
+
+done:
+ blkiocg_css_put(blkcg);
+ return cfqg;
+}
+
/*
- * The cfqd->service_tree holds all pending cfq_queue's that have
+ * 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;
+ /* cfqq reference on cfqg */
+ atomic_inc(&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))
+ return;
+ for_each_cfqg_st(cfqg, i, j, st)
+ BUG_ON(!RB_EMPTY_ROOT(&st->rb) || st->active != NULL);
+ kfree(cfqg);
+}
+
+static void cfq_destroy_cfqg(struct cfq_data *cfqd, struct cfq_group *cfqg)
+{
+ /* Something wrong if we are trying to remove same group twice */
+ BUG_ON(hlist_unhashed(&cfqg->cfqd_node));
+
+ hlist_del_init(&cfqg->cfqd_node);
+
+ /*
+ * Put the reference taken at the time of creation so that when all
+ * queues are gone, group can be destroyed.
+ */
+ cfq_put_cfqg(cfqg);
+}
+
+static void cfq_release_cfq_groups(struct cfq_data *cfqd)
+{
+ struct hlist_node *pos, *n;
+ struct cfq_group *cfqg;
+
+ hlist_for_each_entry_safe(cfqg, pos, n, &cfqd->cfqg_list, cfqd_node) {
+ /*
+ * If cgroup removal path got to blk_group first and removed
+ * it from cgroup list, then it will take care of destroying
+ * cfqg also.
+ */
+ if (!blkiocg_del_blkio_group(&cfqg->blkg))
+ cfq_destroy_cfqg(cfqd, cfqg);
+ }
+}
+
+/*
+ * Blk cgroup controller notification saying that blkio_group object is being
+ * delinked as associated cgroup object is going away. That also means that
+ * no new IO will come in this group. So get rid of this group as soon as
+ * any pending IO in the group is finished.
+ *
+ * This function is called under rcu_read_lock(). key is the rcu protected
+ * pointer. That means "key" is a valid cfq_data pointer as long as we are rcu
+ * read lock.
+ *
+ * "key" was fetched from blkio_group under blkio_cgroup->lock. That means
+ * it should not be NULL as even if elevator was exiting, cgroup deltion
+ * path got to it first.
+ */
+void cfq_unlink_blkio_group(void *key, struct blkio_group *blkg)
+{
+ unsigned long flags;
+ struct cfq_data *cfqd = key;
+
+ spin_lock_irqsave(cfqd->queue->queue_lock, flags);
+ cfq_destroy_cfqg(cfqd, cfqg_of_blkg(blkg));
+ spin_unlock_irqrestore(cfqd->queue->queue_lock, flags);
+}
+
+#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;
+}
+
+static void cfq_release_cfq_groups(struct cfq_data *cfqd) {}
+static inline void cfq_put_cfqg(struct cfq_group *cfqg) {}
+
+#endif /* GROUP_IOSCHED */
+
+/*
+ * 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.
*/
@@ -495,11 +1120,42 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
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;
+ int group_changed = 0;
+
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
+ if (!cfqd->cfq_group_isolation
+ && cfqq_type(cfqq) == SYNC_NOIDLE_WORKLOAD
+ && cfqq->cfqg && cfqq->cfqg != &cfqd->root_group) {
+ /* Move this cfq to root group */
+ cfq_log_cfqq(cfqd, cfqq, "moving to root group");
+ if (!RB_EMPTY_NODE(&cfqq->rb_node))
+ cfq_group_service_tree_del(cfqd, cfqq->cfqg);
+ cfqq->orig_cfqg = cfqq->cfqg;
+ cfqq->cfqg = &cfqd->root_group;
+ atomic_inc(&cfqd->root_group.ref);
+ group_changed = 1;
+ } else if (!cfqd->cfq_group_isolation
+ && cfqq_type(cfqq) == SYNC_WORKLOAD && cfqq->orig_cfqg) {
+ /* cfqq is sequential now needs to go to its original group */
+ BUG_ON(cfqq->cfqg != &cfqd->root_group);
+ if (!RB_EMPTY_NODE(&cfqq->rb_node))
+ cfq_group_service_tree_del(cfqd, cfqq->cfqg);
+ cfq_put_cfqg(cfqq->cfqg);
+ cfqq->cfqg = cfqq->orig_cfqg;
+ cfqq->orig_cfqg = NULL;
+ group_changed = 1;
+ cfq_log_cfqq(cfqd, cfqq, "moved to origin group");
+ }
+#endif
+ 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;
@@ -517,23 +1173,27 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
cfqq->slice_resid = 0;
} else {
rb_key = -HZ;
- __cfqq = cfq_rb_first(&cfqd->service_tree);
+ __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;
@@ -541,35 +1201,28 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
__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 (time_before(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) && !group_changed)
+ return;
+ cfq_group_service_tree_add(cfqd, cfqq->cfqg);
}
static struct cfq_queue *
@@ -671,13 +1324,16 @@ static void cfq_del_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
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--;
}
@@ -688,7 +1344,6 @@ static void cfq_del_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
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]);
@@ -696,8 +1351,17 @@ static void cfq_del_rq_rb(struct request *rq)
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)
@@ -722,7 +1386,7 @@ 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
@@ -829,6 +1493,7 @@ static void
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
*/
@@ -838,6 +1503,8 @@ cfq_merged_requests(struct request_queue *q, struct request *rq,
rq_set_fifo_time(rq, rq_fifo_time(next));
}
+ if (cfqq->next_rq == next)
+ cfqq->next_rq = rq;
cfq_remove_request(next);
}
@@ -848,6 +1515,9 @@ static int cfq_allow_merge(struct request_queue *q, struct request *rq,
struct cfq_io_context *cic;
struct cfq_queue *cfqq;
+ /* Deny merge if bio and rq don't belong to same cfq group */
+ if ((RQ_CFQQ(rq))->cfqg != cfq_get_cfqg(cfqd, 0))
+ return false;
/*
* Disallow merge of a sync bio into an async request.
*/
@@ -871,8 +1541,12 @@ 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->allocated_slice = 0;
cfqq->slice_end = 0;
cfqq->slice_dispatch = 0;
+ cfqq->nr_sectors = 0;
cfq_clear_cfqq_wait_request(cfqq);
cfq_clear_cfqq_must_dispatch(cfqq);
@@ -899,6 +1573,8 @@ __cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq,
del_timer(&cfqd->idle_slice_timer);
cfq_clear_cfqq_wait_request(cfqq);
+ cfq_clear_cfqq_wait_busy(cfqq);
+ cfq_clear_cfqq_wait_busy_done(cfqq);
/*
* store what was left of this slice, if the queue idled/timed out
@@ -908,11 +1584,19 @@ __cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq,
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;
@@ -933,10 +1617,39 @@ static inline void cfq_slice_expired(struct cfq_data *cfqd, bool timed_out)
*/
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;
- return cfq_rb_first(&cfqd->service_tree);
+ /* 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;
+
+ for_each_cfqg_st(cfqg, i, j, st)
+ if ((cfqq = cfq_rb_first(st)) != NULL)
+ return cfqq;
+ return NULL;
}
/*
@@ -945,14 +1658,8 @@ static struct cfq_queue *cfq_get_next_queue(struct cfq_data *cfqd)
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_cfqq_coop_preempt(cfqq))
- cfq_clear_cfqq_coop(cfqq);
- }
-
- if (cfqq)
- cfq_clear_cfqq_coop_preempt(cfqq);
__cfq_set_active_queue(cfqd, cfqq);
return cfqq;