Re: CFQ timer precision

[Jeff Moyer <jmoyer@redhat.com>]

Hi Jan,

Jens Axboe <axboe@kernel.dk> writes:

> On 11/16/2015 08:11 AM, Jan Kara wrote:
>> Hello,
>>
>> lately I was looking into a big performance hit we take when blkio
>> controller is enabled and jbd2 thread ends up in a different cgroup than
>> user process. E.g. dbench4 throughput drops from ~140 MB/s to ~20 MB/s.
>> However artificial dbench4 is, this kind of drop will likely be clearly
>> visible in real life workloads as well. With unified cgroup hierarchy
>> the above cgroup split between jbd2 and user processes is unavoidable
>> once you enable blkio controller so IMO we should accomodate that better.

Is group idle enabled?  What happens if you set that to 0?  What's the
storage?

>> I have couple of CFQ idling improvements / fixes which I'll post later this
>> week once I'll complete some round of benchmarking. They improve the
>> throughput to ~40 MB/s which helps but clearly there's still a big room for
>> improvement. The reason for the performance drop is essentially in idling
>> we do to avoid starvation of CFQ queues. Now when idling in this context,
>> current default of 8 ms idle window is far to large - we start the timer
>> after the final request is completed and thus we effectively give the
>> process 8 ms of CPU time to submit the next IO request. Which I think is
>> usually far too much.

I think I'd need to see blktrace data to make any real sense of this
problem statement.  It's just too vague.

>>                       The problem is that more fine grained idling is
>> actually problematic because e.g. SUSE distro kernels have HZ=250 and thus
>> 1 jiffy is 4 ms. Hence my proposal: Do you think it would be OK to convert
>> CFQ to use highres timers and do all the accounting in microseconds?
>> Then we could tune the idle time to be say 1ms or even autotune it based on
>> process' think time both of which I expect would get us much closer to
>> original throughput (4 ms idle window gets us to ~70 MB/s with my patches,
>> disabling idling gets us to original throughput as expected).
>
> Converting to a non-jiffies timer base should be quite fine. We didn't
> have hrtimers when CFQ was written :-)

I actually have a patch that allows setting slices at the usec
granularity, but didn't go so far as to use hrtimers.  I have no idea
why I wrote it, or whether it works.  ;-) I've attached it in case it's
useful to you, Jan.

Cheers,
Jeff

diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 5da8e6e..fc50fa77 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -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>
@@ -22,23 +22,23 @@
  */
 /* 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 int 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 int cfq_slice_sync = NSEC_PER_SEC / 10;
+static int 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 int cfq_slice_idle = NSEC_PER_SEC / 125;
+static int cfq_group_idle = NSEC_PER_SEC / 125;
+static const int cfq_target_latency = 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
@@ -89,7 +89,7 @@ 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
@@ -104,7 +104,7 @@ 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 */
@@ -125,8 +125,8 @@ struct cfq_queue {
 	unsigned int allocated_slice;
 	unsigned int slice_dispatch;
 	/* time when first request from queue completed and slice started. */
-	unsigned long slice_start;
-	unsigned long slice_end;
+	u64 slice_start;
+	u64 slice_end;
 	long slice_resid;
 
 	/* pending priority requests */
@@ -1046,11 +1046,12 @@ static inline void
 cfq_set_prio_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
 	unsigned 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);
 }
 
 /*
@@ -1062,7 +1063,7 @@ 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;
@@ -1426,27 +1427,27 @@ static inline unsigned int cfq_cfqq_slice_usage(struct cfq_queue *cfqq,
 						unsigned int *unaccounted_time)
 {
 	unsigned int 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(unsigned, (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;
 	}
@@ -1462,6 +1463,7 @@ static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg,
 	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);
@@ -1483,9 +1485,8 @@ 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
@@ -1517,7 +1518,7 @@ 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
@@ -2024,10 +2025,11 @@ 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)) {
@@ -2037,7 +2039,7 @@ 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
@@ -2045,13 +2047,13 @@ 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)) {
@@ -2077,7 +2079,7 @@ 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;
@@ -2377,7 +2379,7 @@ 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;
@@ -2438,7 +2440,7 @@ 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;
@@ -2487,7 +2489,7 @@ __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;
+			cfqq->slice_resid = cfqq->slice_end - ktime_get_ns();
 		cfq_log_cfqq(cfqd, cfqq, "resid=%ld", cfqq->slice_resid);
 	}
 
@@ -2722,6 +2724,7 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
 	struct cfq_queue *cfqq = cfqd->active_queue;
 	struct cfq_io_cq *cic;
 	unsigned long sl, group_idle = 0;
+	u64 now = ktime_get_ns();
 
 	/*
 	 * SSD device without seek penalty, disable idling. But only do so
@@ -2764,7 +2767,7 @@ 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)) {
+	    (cfqq->slice_end - now < cic->ttime.ttime_mean)) {
 		cfq_log_cfqq(cfqd, cfqq, "Not idling. think_time:%lu",
 			     cic->ttime.ttime_mean);
 		return;
@@ -2781,7 +2784,7 @@ 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,
 			group_idle ? 1 : 0);
@@ -2824,7 +2827,7 @@ 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);
@@ -2909,7 +2912,7 @@ static enum wl_type_t cfq_choose_wl_type(struct cfq_data *cfqd,
 		/* 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;
@@ -2927,6 +2930,7 @@ choose_wl_class_and_type(struct cfq_data *cfqd, struct cfq_group *cfqg)
 	struct cfq_rb_root *st;
 	unsigned 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))
@@ -2935,7 +2939,7 @@ 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;
 	}
 
@@ -2953,7 +2957,7 @@ 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:
@@ -2999,7 +3003,7 @@ new_workload:
 
 	slice = max_t(unsigned, slice, CFQ_MIN_TT);
 	cfq_log(cfqd, "workload slice:%d", slice);
-	cfqd->workload_expires = jiffies + slice;
+	cfqd->workload_expires = now + slice;
 }
 
 static struct cfq_group *cfq_get_next_cfqg(struct cfq_data *cfqd)
@@ -3017,16 +3021,17 @@ 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);
 }
@@ -3038,6 +3043,7 @@ 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)
@@ -3109,7 +3115,7 @@ 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);
 	}
@@ -3187,11 +3193,12 @@ 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;
@@ -3266,7 +3273,7 @@ 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;
+		unsigned long last_sync = ktime_get_ns() - cfqd->last_delayed_sync;
 		unsigned int depth;
 
 		depth = last_sync / cfqd->cfq_slice[1];
@@ -3352,7 +3359,7 @@ 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);
 	}
 
@@ -3430,7 +3437,7 @@ 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)
@@ -3694,7 +3701,7 @@ cfq_get_queue(struct cfq_data *cfqd, bool is_sync, struct cfq_io_cq *cic,
 static void
 __cfq_update_io_thinktime(struct cfq_ttime *ttime, unsigned long slice_idle)
 {
-	unsigned long elapsed = jiffies - ttime->last_end_request;
+	unsigned long elapsed = ktime_get_ns() - ttime->last_end_request;
 	elapsed = min(elapsed, 2UL * slice_idle);
 
 	ttime->ttime_samples = (7*ttime->ttime_samples + 256) / 8;
@@ -3947,7 +3954,7 @@ 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,
@@ -3995,6 +4002,7 @@ 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))
@@ -4013,7 +4021,7 @@ 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;
 
 	/*
@@ -4023,7 +4031,7 @@ 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;
@@ -4034,9 +4042,8 @@ 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));
 
@@ -4064,7 +4071,7 @@ 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;
 	}
 
@@ -4092,7 +4099,7 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 			unsigned long extend_sl = cfqd->cfq_slice_idle;
 			if (!cfqd->cfq_slice_idle)
 				extend_sl = cfqd->cfq_group_idle;
-			cfqq->slice_end = jiffies + extend_sl;
+			cfqq->slice_end = now + extend_sl;
 			cfq_mark_cfqq_wait_busy(cfqq);
 			cfq_log_cfqq(cfqd, cfqq, "will busy wait");
 		}
@@ -4468,7 +4475,7 @@ 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:
@@ -4501,7 +4508,7 @@ static ssize_t __FUNC(struct elevator_queue *e, char *page)		\
 	struct cfq_data *cfqd = e->elevator_data;			\
 	unsigned int __data = __VAR;					\
 	if (__CONV)							\
-		__data = jiffies_to_msecs(__data);			\
+		__data = __data / NSEC_PER_MSEC;			\
 	return cfq_var_show(__data, (page));				\
 }
 SHOW_FUNCTION(cfq_quantum_show, cfqd->cfq_quantum, 0);
@@ -4518,6 +4525,20 @@ SHOW_FUNCTION(cfq_low_latency_show, cfqd->cfq_latency, 0);
 SHOW_FUNCTION(cfq_target_latency_show, cfqd->cfq_target_latency, 1);
 #undef SHOW_FUNCTION
 
+#define USEC_SHOW_FUNCTION(__FUNC, __VAR)				\
+static ssize_t __FUNC(struct elevator_queue *e, char *page)		\
+{									\
+	struct cfq_data *cfqd = e->elevator_data;			\
+	unsigned int __data = __VAR;					\
+	__data = __data / NSEC_PER_USEC;				\
+	return cfq_var_show(__data, (page));				\
+}
+USEC_SHOW_FUNCTION(cfq_slice_idle_us_show, cfqd->cfq_slice_idle);
+USEC_SHOW_FUNCTION(cfq_group_idle_us_show, cfqd->cfq_group_idle);
+USEC_SHOW_FUNCTION(cfq_slice_sync_us_show, cfqd->cfq_slice[1]);
+USEC_SHOW_FUNCTION(cfq_slice_async_us_show, cfqd->cfq_slice[0]);
+#undef USEC_SHOW_FUNCTION
+
 #define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV)			\
 static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count)	\
 {									\
@@ -4529,7 +4550,7 @@ 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) = __data * NSEC_PER_MSEC;			\
 	else								\
 		*(__PTR) = __data;					\
 	return ret;							\
@@ -4552,6 +4573,25 @@ STORE_FUNCTION(cfq_low_latency_store, &cfqd->cfq_latency, 0, 1, 0);
 STORE_FUNCTION(cfq_target_latency_store, &cfqd->cfq_target_latency, 1, UINT_MAX, 1);
 #undef STORE_FUNCTION
 
+#define USEC_STORE_FUNCTION(__FUNC, __PTR, MIN, MAX)			\
+static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count)	\
+{									\
+	struct cfq_data *cfqd = e->elevator_data;			\
+	unsigned int __data;						\
+	int ret = cfq_var_store(&__data, (page), count);		\
+	if (__data < (MIN))						\
+		__data = (MIN);						\
+	else if (__data > (MAX))					\
+		__data = (MAX);						\
+	*(__PTR) = __data * NSEC_PER_USEC;				\
+	return ret;							\
+}
+USEC_STORE_FUNCTION(cfq_slice_idle_us_store, &cfqd->cfq_slice_idle, 0, UINT_MAX);
+USEC_STORE_FUNCTION(cfq_group_idle_us_store, &cfqd->cfq_group_idle, 0, UINT_MAX);
+USEC_STORE_FUNCTION(cfq_slice_sync_us_store, &cfqd->cfq_slice[1], 1, UINT_MAX);
+USEC_STORE_FUNCTION(cfq_slice_async_us_store, &cfqd->cfq_slice[0], 1, UINT_MAX);
+#undef USEC_STORE_FUNCTION
+
 #define CFQ_ATTR(name) \
 	__ATTR(name, S_IRUGO|S_IWUSR, cfq_##name##_show, cfq_##name##_store)
 
@@ -4562,10 +4602,14 @@ static struct elv_fs_entry cfq_attrs[] = {
 	CFQ_ATTR(back_seek_max),
 	CFQ_ATTR(back_seek_penalty),
 	CFQ_ATTR(slice_sync),
+	CFQ_ATTR(slice_sync_us),
 	CFQ_ATTR(slice_async),
+	CFQ_ATTR(slice_async_us),
 	CFQ_ATTR(slice_async_rq),
 	CFQ_ATTR(slice_idle),
+	CFQ_ATTR(slice_idle_us),
 	CFQ_ATTR(group_idle),
+	CFQ_ATTR(group_idle_us),
 	CFQ_ATTR(low_latency),
 	CFQ_ATTR(target_latency),
 	__ATTR_NULL