cfq-iosched: Convert from jiffies to nanoseconds
Convert all time-keeping in CFQ IO scheduler from jiffies to nanoseconds so that we can later make the intervals more fine-grained than jiffies. One jiffie is several miliseconds and even for today's rotating disks that is a noticeable amount of time and thus we leave disk unnecessarily idle. Signed-off-by: Jeff Moyer <jmoyer@redhat.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Jens Axboe <axboe@fb.com>
This commit is contained in:
Jeff Moyer
Jens Axboe
parent
28a8f0d317
commit
9a7f38c42c
|
|
@ -10,7 +10,7 @@
|
|||
#include <linux/slab.h>
|
||||
#include <linux/blkdev.h>
|
||||
#include <linux/elevator.h>
|
||||
#include <linux/jiffies.h>
|
||||
#include <linux/ktime.h>
|
||||
#include <linux/rbtree.h>
|
||||
#include <linux/ioprio.h>
|
||||
#include <linux/blktrace_api.h>
|
||||
|
|
@ -22,28 +22,28 @@
|
|||
*/
|
||||
/* max queue in one round of service */
|
||||
static const int cfq_quantum = 8;
|
||||
static const int cfq_fifo_expire[2] = { HZ / 4, HZ / 8 };
|
||||
static const u64 cfq_fifo_expire[2] = { NSEC_PER_SEC / 4, NSEC_PER_SEC / 8 };
|
||||
/* maximum backwards seek, in KiB */
|
||||
static const int cfq_back_max = 16 * 1024;
|
||||
/* penalty of a backwards seek */
|
||||
static const int cfq_back_penalty = 2;
|
||||
static const int cfq_slice_sync = HZ / 10;
|
||||
static int cfq_slice_async = HZ / 25;
|
||||
static const u64 cfq_slice_sync = NSEC_PER_SEC / 10;
|
||||
static u64 cfq_slice_async = NSEC_PER_SEC / 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 u64 cfq_slice_idle = NSEC_PER_SEC / 125;
|
||||
static u64 cfq_group_idle = NSEC_PER_SEC / 125;
|
||||
static const u64 cfq_target_latency = (u64)NSEC_PER_SEC * 3/10; /* 300 ms */
|
||||
static const int cfq_hist_divisor = 4;
|
||||
|
||||
/*
|
||||
* offset from end of service tree
|
||||
*/
|
||||
#define CFQ_IDLE_DELAY (HZ / 5)
|
||||
#define CFQ_IDLE_DELAY (NSEC_PER_SEC / 5)
|
||||
|
||||
/*
|
||||
* below this threshold, we consider thinktime immediate
|
||||
*/
|
||||
#define CFQ_MIN_TT (2)
|
||||
#define CFQ_MIN_TT (2 * NSEC_PER_SEC / HZ)
|
||||
|
||||
#define CFQ_SLICE_SCALE (5)
|
||||
#define CFQ_HW_QUEUE_MIN (5)
|
||||
|
|
@ -73,11 +73,11 @@ static struct kmem_cache *cfq_pool;
|
|||
#define CFQ_WEIGHT_LEGACY_MAX 1000
|
||||
|
||||
struct cfq_ttime {
|
||||
unsigned long last_end_request;
|
||||
u64 last_end_request;
|
||||
|
||||
unsigned long ttime_total;
|
||||
u64 ttime_total;
|
||||
u64 ttime_mean;
|
||||
unsigned long ttime_samples;
|
||||
unsigned long ttime_mean;
|
||||
};
|
||||
|
||||
/*
|
||||
|
|
@ -94,7 +94,7 @@ struct cfq_rb_root {
|
|||
struct cfq_ttime ttime;
|
||||
};
|
||||
#define CFQ_RB_ROOT (struct cfq_rb_root) { .rb = RB_ROOT, \
|
||||
.ttime = {.last_end_request = jiffies,},}
|
||||
.ttime = {.last_end_request = ktime_get_ns(),},}
|
||||
|
||||
/*
|
||||
* Per process-grouping structure
|
||||
|
|
@ -109,7 +109,7 @@ struct cfq_queue {
|
|||
/* service_tree member */
|
||||
struct rb_node rb_node;
|
||||
/* service_tree key */
|
||||
unsigned long rb_key;
|
||||
u64 rb_key;
|
||||
/* prio tree member */
|
||||
struct rb_node p_node;
|
||||
/* prio tree root we belong to, if any */
|
||||
|
|
@ -126,13 +126,13 @@ struct cfq_queue {
|
|||
struct list_head fifo;
|
||||
|
||||
/* time when queue got scheduled in to dispatch first request. */
|
||||
unsigned long dispatch_start;
|
||||
unsigned int allocated_slice;
|
||||
unsigned int slice_dispatch;
|
||||
u64 dispatch_start;
|
||||
u64 allocated_slice;
|
||||
u64 slice_dispatch;
|
||||
/* time when first request from queue completed and slice started. */
|
||||
unsigned long slice_start;
|
||||
unsigned long slice_end;
|
||||
long slice_resid;
|
||||
u64 slice_start;
|
||||
u64 slice_end;
|
||||
u64 slice_resid;
|
||||
|
||||
/* pending priority requests */
|
||||
int prio_pending;
|
||||
|
|
@ -290,7 +290,7 @@ struct cfq_group {
|
|||
struct cfq_rb_root service_trees[2][3];
|
||||
struct cfq_rb_root service_tree_idle;
|
||||
|
||||
unsigned long saved_wl_slice;
|
||||
u64 saved_wl_slice;
|
||||
enum wl_type_t saved_wl_type;
|
||||
enum wl_class_t saved_wl_class;
|
||||
|
||||
|
|
@ -329,7 +329,7 @@ struct cfq_data {
|
|||
*/
|
||||
enum wl_class_t serving_wl_class;
|
||||
enum wl_type_t serving_wl_type;
|
||||
unsigned long workload_expires;
|
||||
u64 workload_expires;
|
||||
struct cfq_group *serving_group;
|
||||
|
||||
/*
|
||||
|
|
@ -374,22 +374,22 @@ struct cfq_data {
|
|||
* tunables, see top of file
|
||||
*/
|
||||
unsigned int cfq_quantum;
|
||||
unsigned int cfq_fifo_expire[2];
|
||||
unsigned int cfq_back_penalty;
|
||||
unsigned int cfq_back_max;
|
||||
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_target_latency;
|
||||
u64 cfq_fifo_expire[2];
|
||||
u64 cfq_slice[2];
|
||||
u64 cfq_slice_idle;
|
||||
u64 cfq_group_idle;
|
||||
u64 cfq_target_latency;
|
||||
|
||||
/*
|
||||
* Fallback dummy cfqq for extreme OOM conditions
|
||||
*/
|
||||
struct cfq_queue oom_cfqq;
|
||||
|
||||
unsigned long last_delayed_sync;
|
||||
u64 last_delayed_sync;
|
||||
};
|
||||
|
||||
static struct cfq_group *cfq_get_next_cfqg(struct cfq_data *cfqd);
|
||||
|
|
@ -676,7 +676,7 @@ static inline void cfqg_stats_update_io_add(struct cfq_group *cfqg,
|
|||
}
|
||||
|
||||
static inline void cfqg_stats_update_timeslice_used(struct cfq_group *cfqg,
|
||||
unsigned long time, unsigned long unaccounted_time)
|
||||
uint64_t time, unsigned long unaccounted_time)
|
||||
{
|
||||
blkg_stat_add(&cfqg->stats.time, time);
|
||||
#ifdef CONFIG_DEBUG_BLK_CGROUP
|
||||
|
|
@ -788,7 +788,7 @@ static inline void cfqg_put(struct cfq_group *cfqg) { }
|
|||
static inline void cfqg_stats_update_io_add(struct cfq_group *cfqg,
|
||||
struct cfq_group *curr_cfqg, int op, int op_flags) { }
|
||||
static inline void cfqg_stats_update_timeslice_used(struct cfq_group *cfqg,
|
||||
unsigned long time, unsigned long unaccounted_time) { }
|
||||
uint64_t time, unsigned long unaccounted_time) { }
|
||||
static inline void cfqg_stats_update_io_remove(struct cfq_group *cfqg, int op,
|
||||
int op_flags) { }
|
||||
static inline void cfqg_stats_update_io_merged(struct cfq_group *cfqg, int op,
|
||||
|
|
@ -815,7 +815,7 @@ static inline void cfqg_stats_update_completion(struct cfq_group *cfqg,
|
|||
static inline bool cfq_io_thinktime_big(struct cfq_data *cfqd,
|
||||
struct cfq_ttime *ttime, bool group_idle)
|
||||
{
|
||||
unsigned long slice;
|
||||
u64 slice;
|
||||
if (!sample_valid(ttime->ttime_samples))
|
||||
return false;
|
||||
if (group_idle)
|
||||
|
|
@ -938,17 +938,18 @@ static inline void cfq_schedule_dispatch(struct cfq_data *cfqd)
|
|||
* 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, bool sync,
|
||||
static inline u64 cfq_prio_slice(struct cfq_data *cfqd, bool sync,
|
||||
unsigned short prio)
|
||||
{
|
||||
const int base_slice = cfqd->cfq_slice[sync];
|
||||
u64 base_slice = cfqd->cfq_slice[sync];
|
||||
u64 slice = div_u64(base_slice, CFQ_SLICE_SCALE);
|
||||
|
||||
WARN_ON(prio >= IOPRIO_BE_NR);
|
||||
|
||||
return base_slice + (base_slice/CFQ_SLICE_SCALE * (4 - prio));
|
||||
return base_slice + (slice * (4 - prio));
|
||||
}
|
||||
|
||||
static inline int
|
||||
static inline u64
|
||||
cfq_prio_to_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
|
||||
{
|
||||
return cfq_prio_slice(cfqd, cfq_cfqq_sync(cfqq), cfqq->ioprio);
|
||||
|
|
@ -966,15 +967,14 @@ cfq_prio_to_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
|
|||
*
|
||||
* The result is also in fixed point w/ CFQ_SERVICE_SHIFT.
|
||||
*/
|
||||
static inline u64 cfqg_scale_charge(unsigned long charge,
|
||||
static inline u64 cfqg_scale_charge(u64 charge,
|
||||
unsigned int vfraction)
|
||||
{
|
||||
u64 c = charge << CFQ_SERVICE_SHIFT; /* make it fixed point */
|
||||
|
||||
/* charge / vfraction */
|
||||
c <<= CFQ_SERVICE_SHIFT;
|
||||
do_div(c, vfraction);
|
||||
return c;
|
||||
return div_u64(c, vfraction);
|
||||
}
|
||||
|
||||
static inline u64 max_vdisktime(u64 min_vdisktime, u64 vdisktime)
|
||||
|
|
@ -1027,16 +1027,16 @@ static inline unsigned cfq_group_get_avg_queues(struct cfq_data *cfqd,
|
|||
return cfqg->busy_queues_avg[rt];
|
||||
}
|
||||
|
||||
static inline unsigned
|
||||
static inline u64
|
||||
cfq_group_slice(struct cfq_data *cfqd, struct cfq_group *cfqg)
|
||||
{
|
||||
return cfqd->cfq_target_latency * cfqg->vfraction >> CFQ_SERVICE_SHIFT;
|
||||
}
|
||||
|
||||
static inline unsigned
|
||||
static inline u64
|
||||
cfq_scaled_cfqq_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
|
||||
{
|
||||
unsigned slice = cfq_prio_to_slice(cfqd, cfqq);
|
||||
u64 slice = cfq_prio_to_slice(cfqd, cfqq);
|
||||
if (cfqd->cfq_latency) {
|
||||
/*
|
||||
* interested queues (we consider only the ones with the same
|
||||
|
|
@ -1044,20 +1044,22 @@ cfq_scaled_cfqq_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
|
|||
*/
|
||||
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);
|
||||
u64 sync_slice = cfqd->cfq_slice[1];
|
||||
u64 expect_latency = sync_slice * iq;
|
||||
u64 group_slice = cfq_group_slice(cfqd, cfqq->cfqg);
|
||||
|
||||
if (expect_latency > group_slice) {
|
||||
unsigned base_low_slice = 2 * cfqd->cfq_slice_idle;
|
||||
u64 base_low_slice = 2 * cfqd->cfq_slice_idle;
|
||||
u64 low_slice;
|
||||
|
||||
/* scale low_slice according to IO priority
|
||||
* and sync vs async */
|
||||
unsigned low_slice =
|
||||
min(slice, base_low_slice * slice / sync_slice);
|
||||
low_slice = div64_u64(base_low_slice*slice, sync_slice);
|
||||
low_slice = min(slice, low_slice);
|
||||
/* the adapted slice value is scaled to fit all iqs
|
||||
* into the target latency */
|
||||
slice = max(slice * group_slice / expect_latency,
|
||||
low_slice);
|
||||
slice = div64_u64(slice*group_slice, expect_latency);
|
||||
slice = max(slice, low_slice);
|
||||
}
|
||||
}
|
||||
return slice;
|
||||
|
|
@ -1066,12 +1068,13 @@ cfq_scaled_cfqq_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
|
|||
static inline void
|
||||
cfq_set_prio_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
|
||||
{
|
||||
unsigned slice = cfq_scaled_cfqq_slice(cfqd, cfqq);
|
||||
u64 slice = cfq_scaled_cfqq_slice(cfqd, cfqq);
|
||||
u64 now = ktime_get_ns();
|
||||
|
||||
cfqq->slice_start = jiffies;
|
||||
cfqq->slice_end = jiffies + slice;
|
||||
cfqq->slice_start = now;
|
||||
cfqq->slice_end = now + slice;
|
||||
cfqq->allocated_slice = slice;
|
||||
cfq_log_cfqq(cfqd, cfqq, "set_slice=%lu", cfqq->slice_end - jiffies);
|
||||
cfq_log_cfqq(cfqd, cfqq, "set_slice=%llu", cfqq->slice_end - now);
|
||||
}
|
||||
|
||||
/*
|
||||
|
|
@ -1083,7 +1086,7 @@ static inline bool cfq_slice_used(struct cfq_queue *cfqq)
|
|||
{
|
||||
if (cfq_cfqq_slice_new(cfqq))
|
||||
return false;
|
||||
if (time_before(jiffies, cfqq->slice_end))
|
||||
if (ktime_get_ns() < cfqq->slice_end)
|
||||
return false;
|
||||
|
||||
return true;
|
||||
|
|
@ -1249,8 +1252,8 @@ cfq_find_next_rq(struct cfq_data *cfqd, struct cfq_queue *cfqq,
|
|||
return cfq_choose_req(cfqd, next, prev, blk_rq_pos(last));
|
||||
}
|
||||
|
||||
static unsigned long cfq_slice_offset(struct cfq_data *cfqd,
|
||||
struct cfq_queue *cfqq)
|
||||
static u64 cfq_slice_offset(struct cfq_data *cfqd,
|
||||
struct cfq_queue *cfqq)
|
||||
{
|
||||
/*
|
||||
* just an approximation, should be ok.
|
||||
|
|
@ -1443,31 +1446,31 @@ cfq_group_notify_queue_del(struct cfq_data *cfqd, struct cfq_group *cfqg)
|
|||
cfqg_stats_update_dequeue(cfqg);
|
||||
}
|
||||
|
||||
static inline unsigned int cfq_cfqq_slice_usage(struct cfq_queue *cfqq,
|
||||
unsigned int *unaccounted_time)
|
||||
static inline u64 cfq_cfqq_slice_usage(struct cfq_queue *cfqq,
|
||||
u64 *unaccounted_time)
|
||||
{
|
||||
unsigned int slice_used;
|
||||
u64 slice_used;
|
||||
u64 now = ktime_get_ns();
|
||||
|
||||
/*
|
||||
* 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) {
|
||||
if (!cfqq->slice_start || cfqq->slice_start == now) {
|
||||
/*
|
||||
* 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);
|
||||
slice_used = max_t(u64, (now - cfqq->dispatch_start), 1);
|
||||
} else {
|
||||
slice_used = jiffies - cfqq->slice_start;
|
||||
slice_used = now - cfqq->slice_start;
|
||||
if (slice_used > cfqq->allocated_slice) {
|
||||
*unaccounted_time = slice_used - cfqq->allocated_slice;
|
||||
slice_used = cfqq->allocated_slice;
|
||||
}
|
||||
if (time_after(cfqq->slice_start, cfqq->dispatch_start))
|
||||
if (cfqq->slice_start > cfqq->dispatch_start)
|
||||
*unaccounted_time += cfqq->slice_start -
|
||||
cfqq->dispatch_start;
|
||||
}
|
||||
|
|
@ -1479,10 +1482,11 @@ 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, unaccounted_sl = 0;
|
||||
u64 used_sl, charge, unaccounted_sl = 0;
|
||||
int nr_sync = cfqg->nr_cfqq - cfqg_busy_async_queues(cfqd, cfqg)
|
||||
- cfqg->service_tree_idle.count;
|
||||
unsigned int vfr;
|
||||
u64 now = ktime_get_ns();
|
||||
|
||||
BUG_ON(nr_sync < 0);
|
||||
used_sl = charge = cfq_cfqq_slice_usage(cfqq, &unaccounted_sl);
|
||||
|
|
@ -1504,9 +1508,8 @@ static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *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_wl_slice = cfqd->workload_expires
|
||||
- jiffies;
|
||||
if (cfqd->workload_expires > now) {
|
||||
cfqg->saved_wl_slice = cfqd->workload_expires - now;
|
||||
cfqg->saved_wl_type = cfqd->serving_wl_type;
|
||||
cfqg->saved_wl_class = cfqd->serving_wl_class;
|
||||
} else
|
||||
|
|
@ -1515,7 +1518,7 @@ static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg,
|
|||
cfq_log_cfqg(cfqd, cfqg, "served: vt=%llu min_vt=%llu", cfqg->vdisktime,
|
||||
st->min_vdisktime);
|
||||
cfq_log_cfqq(cfqq->cfqd, cfqq,
|
||||
"sl_used=%u disp=%u charge=%u iops=%u sect=%lu",
|
||||
"sl_used=%llu disp=%llu charge=%llu iops=%u sect=%lu",
|
||||
used_sl, cfqq->slice_dispatch, charge,
|
||||
iops_mode(cfqd), cfqq->nr_sectors);
|
||||
cfqg_stats_update_timeslice_used(cfqg, used_sl, unaccounted_sl);
|
||||
|
|
@ -1538,7 +1541,7 @@ static void cfq_init_cfqg_base(struct cfq_group *cfqg)
|
|||
*st = CFQ_RB_ROOT;
|
||||
RB_CLEAR_NODE(&cfqg->rb_node);
|
||||
|
||||
cfqg->ttime.last_end_request = jiffies;
|
||||
cfqg->ttime.last_end_request = ktime_get_ns();
|
||||
}
|
||||
|
||||
#ifdef CONFIG_CFQ_GROUP_IOSCHED
|
||||
|
|
@ -2221,10 +2224,11 @@ 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;
|
||||
u64 rb_key;
|
||||
struct cfq_rb_root *st;
|
||||
int left;
|
||||
int new_cfqq = 1;
|
||||
u64 now = ktime_get_ns();
|
||||
|
||||
st = st_for(cfqq->cfqg, cfqq_class(cfqq), cfqq_type(cfqq));
|
||||
if (cfq_class_idle(cfqq)) {
|
||||
|
|
@ -2234,7 +2238,7 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
|
|||
__cfqq = rb_entry(parent, struct cfq_queue, rb_node);
|
||||
rb_key += __cfqq->rb_key;
|
||||
} else
|
||||
rb_key += jiffies;
|
||||
rb_key += now;
|
||||
} else if (!add_front) {
|
||||
/*
|
||||
* Get our rb key offset. Subtract any residual slice
|
||||
|
|
@ -2242,13 +2246,13 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
|
|||
* 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 = cfq_slice_offset(cfqd, cfqq) + now;
|
||||
rb_key -= cfqq->slice_resid;
|
||||
cfqq->slice_resid = 0;
|
||||
} else {
|
||||
rb_key = -HZ;
|
||||
rb_key = -NSEC_PER_SEC;
|
||||
__cfqq = cfq_rb_first(st);
|
||||
rb_key += __cfqq ? __cfqq->rb_key : jiffies;
|
||||
rb_key += __cfqq ? __cfqq->rb_key : now;
|
||||
}
|
||||
|
||||
if (!RB_EMPTY_NODE(&cfqq->rb_node)) {
|
||||
|
|
@ -2274,7 +2278,7 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
|
|||
/*
|
||||
* sort by key, that represents service time.
|
||||
*/
|
||||
if (time_before(rb_key, __cfqq->rb_key))
|
||||
if (rb_key < __cfqq->rb_key)
|
||||
p = &parent->rb_left;
|
||||
else {
|
||||
p = &parent->rb_right;
|
||||
|
|
@ -2574,7 +2578,7 @@ cfq_merged_requests(struct request_queue *q, struct request *rq,
|
|||
* reposition in fifo if next is older than rq
|
||||
*/
|
||||
if (!list_empty(&rq->queuelist) && !list_empty(&next->queuelist) &&
|
||||
time_before(next->fifo_time, rq->fifo_time) &&
|
||||
next->fifo_time < rq->fifo_time &&
|
||||
cfqq == RQ_CFQQ(next)) {
|
||||
list_move(&rq->queuelist, &next->queuelist);
|
||||
rq->fifo_time = next->fifo_time;
|
||||
|
|
@ -2635,7 +2639,7 @@ static void __cfq_set_active_queue(struct cfq_data *cfqd,
|
|||
cfqd->serving_wl_class, cfqd->serving_wl_type);
|
||||
cfqg_stats_update_avg_queue_size(cfqq->cfqg);
|
||||
cfqq->slice_start = 0;
|
||||
cfqq->dispatch_start = jiffies;
|
||||
cfqq->dispatch_start = ktime_get_ns();
|
||||
cfqq->allocated_slice = 0;
|
||||
cfqq->slice_end = 0;
|
||||
cfqq->slice_dispatch = 0;
|
||||
|
|
@ -2684,8 +2688,8 @@ __cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq,
|
|||
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);
|
||||
cfqq->slice_resid = cfqq->slice_end - ktime_get_ns();
|
||||
cfq_log_cfqq(cfqd, cfqq, "resid=%llu", cfqq->slice_resid);
|
||||
}
|
||||
|
||||
cfq_group_served(cfqd, cfqq->cfqg, cfqq);
|
||||
|
|
@ -2919,7 +2923,8 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
|
|||
struct cfq_queue *cfqq = cfqd->active_queue;
|
||||
struct cfq_rb_root *st = cfqq->service_tree;
|
||||
struct cfq_io_cq *cic;
|
||||
unsigned long sl, group_idle = 0;
|
||||
u64 sl, group_idle = 0;
|
||||
u64 now = ktime_get_ns();
|
||||
|
||||
/*
|
||||
* SSD device without seek penalty, disable idling. But only do so
|
||||
|
|
@ -2962,8 +2967,8 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
|
|||
* time slice.
|
||||
*/
|
||||
if (sample_valid(cic->ttime.ttime_samples) &&
|
||||
(cfqq->slice_end - jiffies < cic->ttime.ttime_mean)) {
|
||||
cfq_log_cfqq(cfqd, cfqq, "Not idling. think_time:%lu",
|
||||
(cfqq->slice_end - now < cic->ttime.ttime_mean)) {
|
||||
cfq_log_cfqq(cfqd, cfqq, "Not idling. think_time:%llu",
|
||||
cic->ttime.ttime_mean);
|
||||
return;
|
||||
}
|
||||
|
|
@ -2984,9 +2989,9 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
|
|||
else
|
||||
sl = cfqd->cfq_slice_idle;
|
||||
|
||||
mod_timer(&cfqd->idle_slice_timer, jiffies + sl);
|
||||
mod_timer(&cfqd->idle_slice_timer, now + sl);
|
||||
cfqg_stats_set_start_idle_time(cfqq->cfqg);
|
||||
cfq_log_cfqq(cfqd, cfqq, "arm_idle: %lu group_idle: %d", sl,
|
||||
cfq_log_cfqq(cfqd, cfqq, "arm_idle: %llu group_idle: %d", sl,
|
||||
group_idle ? 1 : 0);
|
||||
}
|
||||
|
||||
|
|
@ -3026,7 +3031,7 @@ static struct request *cfq_check_fifo(struct cfq_queue *cfqq)
|
|||
return NULL;
|
||||
|
||||
rq = rq_entry_fifo(cfqq->fifo.next);
|
||||
if (time_before(jiffies, rq->fifo_time))
|
||||
if (ktime_get_ns() < rq->fifo_time)
|
||||
rq = NULL;
|
||||
|
||||
cfq_log_cfqq(cfqq->cfqd, cfqq, "fifo=%p", rq);
|
||||
|
|
@ -3104,14 +3109,14 @@ static enum wl_type_t cfq_choose_wl_type(struct cfq_data *cfqd,
|
|||
struct cfq_queue *queue;
|
||||
int i;
|
||||
bool key_valid = false;
|
||||
unsigned long lowest_key = 0;
|
||||
u64 lowest_key = 0;
|
||||
enum wl_type_t cur_best = SYNC_NOIDLE_WORKLOAD;
|
||||
|
||||
for (i = 0; i <= SYNC_WORKLOAD; ++i) {
|
||||
/* select the one with lowest rb_key */
|
||||
queue = cfq_rb_first(st_for(cfqg, wl_class, i));
|
||||
if (queue &&
|
||||
(!key_valid || time_before(queue->rb_key, lowest_key))) {
|
||||
(!key_valid || queue->rb_key < lowest_key)) {
|
||||
lowest_key = queue->rb_key;
|
||||
cur_best = i;
|
||||
key_valid = true;
|
||||
|
|
@ -3124,11 +3129,12 @@ static enum wl_type_t cfq_choose_wl_type(struct cfq_data *cfqd,
|
|||
static void
|
||||
choose_wl_class_and_type(struct cfq_data *cfqd, struct cfq_group *cfqg)
|
||||
{
|
||||
unsigned slice;
|
||||
u64 slice;
|
||||
unsigned count;
|
||||
struct cfq_rb_root *st;
|
||||
unsigned group_slice;
|
||||
u64 group_slice;
|
||||
enum wl_class_t original_class = cfqd->serving_wl_class;
|
||||
u64 now = ktime_get_ns();
|
||||
|
||||
/* Choose next priority. RT > BE > IDLE */
|
||||
if (cfq_group_busy_queues_wl(RT_WORKLOAD, cfqd, cfqg))
|
||||
|
|
@ -3137,7 +3143,7 @@ choose_wl_class_and_type(struct cfq_data *cfqd, struct cfq_group *cfqg)
|
|||
cfqd->serving_wl_class = BE_WORKLOAD;
|
||||
else {
|
||||
cfqd->serving_wl_class = IDLE_WORKLOAD;
|
||||
cfqd->workload_expires = jiffies + 1;
|
||||
cfqd->workload_expires = now + jiffies_to_nsecs(1);
|
||||
return;
|
||||
}
|
||||
|
||||
|
|
@ -3155,7 +3161,7 @@ choose_wl_class_and_type(struct cfq_data *cfqd, struct cfq_group *cfqg)
|
|||
/*
|
||||
* check workload expiration, and that we still have other queues ready
|
||||
*/
|
||||
if (count && !time_after(jiffies, cfqd->workload_expires))
|
||||
if (count && !(now > cfqd->workload_expires))
|
||||
return;
|
||||
|
||||
new_workload:
|
||||
|
|
@ -3172,13 +3178,13 @@ new_workload:
|
|||
*/
|
||||
group_slice = cfq_group_slice(cfqd, cfqg);
|
||||
|
||||
slice = group_slice * count /
|
||||
slice = div_u64(group_slice * count,
|
||||
max_t(unsigned, cfqg->busy_queues_avg[cfqd->serving_wl_class],
|
||||
cfq_group_busy_queues_wl(cfqd->serving_wl_class, cfqd,
|
||||
cfqg));
|
||||
cfqg)));
|
||||
|
||||
if (cfqd->serving_wl_type == ASYNC_WORKLOAD) {
|
||||
unsigned int tmp;
|
||||
u64 tmp;
|
||||
|
||||
/*
|
||||
* Async queues are currently system wide. Just taking
|
||||
|
|
@ -3189,19 +3195,19 @@ new_workload:
|
|||
*/
|
||||
tmp = cfqd->cfq_target_latency *
|
||||
cfqg_busy_async_queues(cfqd, cfqg);
|
||||
tmp = tmp/cfqd->busy_queues;
|
||||
slice = min_t(unsigned, slice, tmp);
|
||||
tmp = div_u64(tmp, cfqd->busy_queues);
|
||||
slice = min_t(u64, slice, tmp);
|
||||
|
||||
/* async workload slice is scaled down according to
|
||||
* the sync/async slice ratio. */
|
||||
slice = slice * cfqd->cfq_slice[0] / cfqd->cfq_slice[1];
|
||||
slice = div64_u64(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);
|
||||
cfq_log(cfqd, "workload slice:%d", slice);
|
||||
cfqd->workload_expires = jiffies + slice;
|
||||
slice = max_t(u64, slice, CFQ_MIN_TT);
|
||||
cfq_log(cfqd, "workload slice:%llu", slice);
|
||||
cfqd->workload_expires = now + slice;
|
||||
}
|
||||
|
||||
static struct cfq_group *cfq_get_next_cfqg(struct cfq_data *cfqd)
|
||||
|
|
@ -3219,16 +3225,17 @@ static struct cfq_group *cfq_get_next_cfqg(struct cfq_data *cfqd)
|
|||
static void cfq_choose_cfqg(struct cfq_data *cfqd)
|
||||
{
|
||||
struct cfq_group *cfqg = cfq_get_next_cfqg(cfqd);
|
||||
u64 now = ktime_get_ns();
|
||||
|
||||
cfqd->serving_group = cfqg;
|
||||
|
||||
/* Restore the workload type data */
|
||||
if (cfqg->saved_wl_slice) {
|
||||
cfqd->workload_expires = jiffies + cfqg->saved_wl_slice;
|
||||
cfqd->workload_expires = now + cfqg->saved_wl_slice;
|
||||
cfqd->serving_wl_type = cfqg->saved_wl_type;
|
||||
cfqd->serving_wl_class = cfqg->saved_wl_class;
|
||||
} else
|
||||
cfqd->workload_expires = jiffies - 1;
|
||||
cfqd->workload_expires = now - 1;
|
||||
|
||||
choose_wl_class_and_type(cfqd, cfqg);
|
||||
}
|
||||
|
|
@ -3240,6 +3247,7 @@ static void cfq_choose_cfqg(struct cfq_data *cfqd)
|
|||
static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
|
||||
{
|
||||
struct cfq_queue *cfqq, *new_cfqq = NULL;
|
||||
u64 now = ktime_get_ns();
|
||||
|
||||
cfqq = cfqd->active_queue;
|
||||
if (!cfqq)
|
||||
|
|
@ -3311,7 +3319,7 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
|
|||
**/
|
||||
if (CFQQ_SEEKY(cfqq) && cfq_cfqq_idle_window(cfqq) &&
|
||||
(cfq_cfqq_slice_new(cfqq) ||
|
||||
(cfqq->slice_end - jiffies > jiffies - cfqq->slice_start))) {
|
||||
(cfqq->slice_end - now > now - cfqq->slice_start))) {
|
||||
cfq_clear_cfqq_deep(cfqq);
|
||||
cfq_clear_cfqq_idle_window(cfqq);
|
||||
}
|
||||
|
|
@ -3389,11 +3397,12 @@ static int cfq_forced_dispatch(struct cfq_data *cfqd)
|
|||
static inline bool cfq_slice_used_soon(struct cfq_data *cfqd,
|
||||
struct cfq_queue *cfqq)
|
||||
{
|
||||
u64 now = ktime_get_ns();
|
||||
|
||||
/* the queue hasn't finished any request, can't estimate */
|
||||
if (cfq_cfqq_slice_new(cfqq))
|
||||
return true;
|
||||
if (time_after(jiffies + cfqd->cfq_slice_idle * cfqq->dispatched,
|
||||
cfqq->slice_end))
|
||||
if (now + cfqd->cfq_slice_idle * cfqq->dispatched > cfqq->slice_end)
|
||||
return true;
|
||||
|
||||
return false;
|
||||
|
|
@ -3468,10 +3477,10 @@ static bool cfq_may_dispatch(struct cfq_data *cfqd, struct cfq_queue *cfqq)
|
|||
* based on the last sync IO we serviced
|
||||
*/
|
||||
if (!cfq_cfqq_sync(cfqq) && cfqd->cfq_latency) {
|
||||
unsigned long last_sync = jiffies - cfqd->last_delayed_sync;
|
||||
u64 last_sync = ktime_get_ns() - cfqd->last_delayed_sync;
|
||||
unsigned int depth;
|
||||
|
||||
depth = last_sync / cfqd->cfq_slice[1];
|
||||
depth = div64_u64(last_sync, cfqd->cfq_slice[1]);
|
||||
if (!depth && !cfqq->dispatched)
|
||||
depth = 1;
|
||||
if (depth < max_dispatch)
|
||||
|
|
@ -3554,7 +3563,7 @@ static int cfq_dispatch_requests(struct request_queue *q, int force)
|
|||
if (cfqd->busy_queues > 1 && ((!cfq_cfqq_sync(cfqq) &&
|
||||
cfqq->slice_dispatch >= cfq_prio_to_maxrq(cfqd, cfqq)) ||
|
||||
cfq_class_idle(cfqq))) {
|
||||
cfqq->slice_end = jiffies + 1;
|
||||
cfqq->slice_end = ktime_get_ns() + 1;
|
||||
cfq_slice_expired(cfqd, 0);
|
||||
}
|
||||
|
||||
|
|
@ -3632,7 +3641,7 @@ static void cfq_init_icq(struct io_cq *icq)
|
|||
{
|
||||
struct cfq_io_cq *cic = icq_to_cic(icq);
|
||||
|
||||
cic->ttime.last_end_request = jiffies;
|
||||
cic->ttime.last_end_request = ktime_get_ns();
|
||||
}
|
||||
|
||||
static void cfq_exit_icq(struct io_cq *icq)
|
||||
|
|
@ -3853,14 +3862,15 @@ out:
|
|||
}
|
||||
|
||||
static void
|
||||
__cfq_update_io_thinktime(struct cfq_ttime *ttime, unsigned long slice_idle)
|
||||
__cfq_update_io_thinktime(struct cfq_ttime *ttime, u64 slice_idle)
|
||||
{
|
||||
unsigned long elapsed = jiffies - ttime->last_end_request;
|
||||
u64 elapsed = ktime_get_ns() - ttime->last_end_request;
|
||||
elapsed = min(elapsed, 2UL * slice_idle);
|
||||
|
||||
ttime->ttime_samples = (7*ttime->ttime_samples + 256) / 8;
|
||||
ttime->ttime_total = (7*ttime->ttime_total + 256*elapsed) / 8;
|
||||
ttime->ttime_mean = (ttime->ttime_total + 128) / ttime->ttime_samples;
|
||||
ttime->ttime_total = div_u64(7*ttime->ttime_total + 256*elapsed, 8);
|
||||
ttime->ttime_mean = div64_ul(ttime->ttime_total + 128,
|
||||
ttime->ttime_samples);
|
||||
}
|
||||
|
||||
static void
|
||||
|
|
@ -4113,7 +4123,7 @@ static void cfq_insert_request(struct request_queue *q, struct request *rq)
|
|||
cfq_log_cfqq(cfqd, cfqq, "insert_request");
|
||||
cfq_init_prio_data(cfqq, RQ_CIC(rq));
|
||||
|
||||
rq->fifo_time = jiffies + cfqd->cfq_fifo_expire[rq_is_sync(rq)];
|
||||
rq->fifo_time = ktime_get_ns() + cfqd->cfq_fifo_expire[rq_is_sync(rq)];
|
||||
list_add_tail(&rq->queuelist, &cfqq->fifo);
|
||||
cfq_add_rq_rb(rq);
|
||||
cfqg_stats_update_io_add(RQ_CFQG(rq), cfqd->serving_group, req_op(rq),
|
||||
|
|
@ -4161,6 +4171,7 @@ static void cfq_update_hw_tag(struct cfq_data *cfqd)
|
|||
static bool cfq_should_wait_busy(struct cfq_data *cfqd, struct cfq_queue *cfqq)
|
||||
{
|
||||
struct cfq_io_cq *cic = cfqd->active_cic;
|
||||
u64 now = ktime_get_ns();
|
||||
|
||||
/* If the queue already has requests, don't wait */
|
||||
if (!RB_EMPTY_ROOT(&cfqq->sort_list))
|
||||
|
|
@ -4179,7 +4190,7 @@ static bool cfq_should_wait_busy(struct cfq_data *cfqd, struct cfq_queue *cfqq)
|
|||
|
||||
/* if slice left is less than think time, wait busy */
|
||||
if (cic && sample_valid(cic->ttime.ttime_samples)
|
||||
&& (cfqq->slice_end - jiffies < cic->ttime.ttime_mean))
|
||||
&& (cfqq->slice_end - now < cic->ttime.ttime_mean))
|
||||
return true;
|
||||
|
||||
/*
|
||||
|
|
@ -4189,7 +4200,7 @@ static bool cfq_should_wait_busy(struct cfq_data *cfqd, struct cfq_queue *cfqq)
|
|||
* case where think time is less than a jiffy, mark the queue wait
|
||||
* busy if only 1 jiffy is left in the slice.
|
||||
*/
|
||||
if (cfqq->slice_end - jiffies == 1)
|
||||
if (cfqq->slice_end - now <= jiffies_to_nsecs(1))
|
||||
return true;
|
||||
|
||||
return false;
|
||||
|
|
@ -4200,9 +4211,8 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
|
|||
struct cfq_queue *cfqq = RQ_CFQQ(rq);
|
||||
struct cfq_data *cfqd = cfqq->cfqd;
|
||||
const int sync = rq_is_sync(rq);
|
||||
unsigned long now;
|
||||
u64 now = ktime_get_ns();
|
||||
|
||||
now = jiffies;
|
||||
cfq_log_cfqq(cfqd, cfqq, "complete rqnoidle %d",
|
||||
!!(rq->cmd_flags & REQ_NOIDLE));
|
||||
|
||||
|
|
@ -4231,7 +4241,7 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
|
|||
cfqq_type(cfqq));
|
||||
|
||||
st->ttime.last_end_request = now;
|
||||
if (!time_after(rq->start_time + cfqd->cfq_fifo_expire[1], now))
|
||||
if (!(rq->start_time + cfqd->cfq_fifo_expire[1] > now))
|
||||
cfqd->last_delayed_sync = now;
|
||||
}
|
||||
|
||||
|
|
@ -4256,10 +4266,10 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
|
|||
* the queue.
|
||||
*/
|
||||
if (cfq_should_wait_busy(cfqd, cfqq)) {
|
||||
unsigned long extend_sl = cfqd->cfq_slice_idle;
|
||||
u64 extend_sl = cfqd->cfq_slice_idle;
|
||||
if (!cfqd->cfq_slice_idle)
|
||||
extend_sl = cfqd->cfq_group_idle;
|
||||
cfqq->slice_end = jiffies + extend_sl;
|
||||
cfqq->slice_end = now + extend_sl;
|
||||
cfq_mark_cfqq_wait_busy(cfqq);
|
||||
cfq_log_cfqq(cfqd, cfqq, "will busy wait");
|
||||
}
|
||||
|
|
@ -4618,7 +4628,7 @@ static int cfq_init_queue(struct request_queue *q, struct elevator_type *e)
|
|||
* we optimistically start assuming sync ops weren't delayed in last
|
||||
* second, in order to have larger depth for async operations.
|
||||
*/
|
||||
cfqd->last_delayed_sync = jiffies - HZ;
|
||||
cfqd->last_delayed_sync = ktime_get_ns() - NSEC_PER_SEC;
|
||||
return 0;
|
||||
|
||||
out_free:
|
||||
|
|
@ -4661,9 +4671,9 @@ cfq_var_store(unsigned int *var, const char *page, size_t count)
|
|||
static ssize_t __FUNC(struct elevator_queue *e, char *page) \
|
||||
{ \
|
||||
struct cfq_data *cfqd = e->elevator_data; \
|
||||
unsigned int __data = __VAR; \
|
||||
u64 __data = __VAR; \
|
||||
if (__CONV) \
|
||||
__data = jiffies_to_msecs(__data); \
|
||||
__data = div_u64(__data, NSEC_PER_MSEC); \
|
||||
return cfq_var_show(__data, (page)); \
|
||||
}
|
||||
SHOW_FUNCTION(cfq_quantum_show, cfqd->cfq_quantum, 0);
|
||||
|
|
@ -4691,7 +4701,7 @@ static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count)
|
|||
else if (__data > (MAX)) \
|
||||
__data = (MAX); \
|
||||
if (__CONV) \
|
||||
*(__PTR) = msecs_to_jiffies(__data); \
|
||||
*(__PTR) = (u64)__data * NSEC_PER_MSEC; \
|
||||
else \
|
||||
*(__PTR) = __data; \
|
||||
return ret; \
|
||||
|
|
@ -4785,18 +4795,7 @@ static int __init cfq_init(void)
|
|||
{
|
||||
int ret;
|
||||
|
||||
/*
|
||||
* could be 0 on HZ < 1000 setups
|
||||
*/
|
||||
if (!cfq_slice_async)
|
||||
cfq_slice_async = 1;
|
||||
if (!cfq_slice_idle)
|
||||
cfq_slice_idle = 1;
|
||||
|
||||
#ifdef CONFIG_CFQ_GROUP_IOSCHED
|
||||
if (!cfq_group_idle)
|
||||
cfq_group_idle = 1;
|
||||
|
||||
ret = blkcg_policy_register(&blkcg_policy_cfq);
|
||||
if (ret)
|
||||
return ret;
|
||||
|
|
|
|||
Loading…
Reference in New Issue