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;
};
/* 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;
/*
* The priority currently being served
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;
*/
struct cfq_queue oom_cfqq;
- unsigned long last_end_sync_rq;
+ unsigned long last_delayed_sync;
/* 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)
+ enum wl_type_t type)
{
if (!cfqg)
return NULL;
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) \
CFQ_CFQQ_FNS(coop);
CFQ_CFQQ_FNS(deep);
CFQ_CFQQ_FNS(wait_busy);
-CFQ_CFQQ_FNS(wait_busy_done);
#undef CFQ_CFQQ_FNS
#ifdef CONFIG_DEBUG_CFQ_IOSCHED
__cfq_group_service_tree_add(st, cfqg);
cfqg->on_st = true;
- cfqd->nr_groups++;
st->total_weight += cfqg->weight;
}
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);
unsigned int major, minor;
/* Do we need to take this reference */
- if (!css_tryget(&blkcg->css))
+ if (!blkiocg_css_tryget(blkcg))
return NULL;;
cfqg = cfqg_of_blkg(blkiocg_lookup_group(blkcg, key));
hlist_add_head(&cfqg->cfqd_node, &cfqd->cfqg_list);
done:
- css_put(&blkcg->css);
+ blkiocg_css_put(blkcg);
return cfqg;
}
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);
+ cfqq_type(cfqq));
if (cfq_class_idle(cfqq)) {
rb_key = CFQ_IDLE_DELAY;
parent = rb_last(&service_tree->rb);
rb_link_node(&cfqq->rb_node, parent, p);
rb_insert_color(&cfqq->rb_node, &service_tree->rb);
service_tree->count++;
- if (add_front || !new_cfqq)
+ if ((add_front || !new_cfqq) && !group_changed)
return;
cfq_group_service_tree_add(cfqd, cfqq->cfqg);
}
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.
*/
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
{
struct cfq_rb_root *service_tree =
service_tree_for(cfqd->serving_group, cfqd->serving_prio,
- cfqd->serving_type, cfqd);
+ cfqd->serving_type);
if (!cfqd->rq_queued)
return NULL;
#define CFQQ_SEEKY(cfqq) ((cfqq)->seek_mean > CFQQ_SEEK_THR)
static inline int cfq_rq_close(struct cfq_data *cfqd, struct cfq_queue *cfqq,
- struct request *rq)
+ struct request *rq, bool for_preempt)
{
sector_t sdist = cfqq->seek_mean;
if (!sample_valid(cfqq->seek_samples))
sdist = CFQQ_SEEK_THR;
+ /* if seek_mean is big, using it as close criteria is meaningless */
+ if (sdist > CFQQ_SEEK_THR && !for_preempt)
+ 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, cur_cfqq, __cfqq->next_rq))
+ if (cfq_rq_close(cfqd, cur_cfqq, __cfqq->next_rq, false))
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, cur_cfqq, __cfqq->next_rq))
+ if (cfq_rq_close(cfqd, cur_cfqq, __cfqq->next_rq, false))
return __cfqq;
return NULL;
return NULL;
/*
+ * Don't search priority tree if it's the only queue in the group.
+ */
+ if (cur_cfqq->cfqg->nr_cfqq == 1)
+ return NULL;
+
+ /*
* We should notice if some of the queues are cooperating, eg
* working closely on the same area of the disk. In that case,
* we can group them together and don't waste time idling.
return false;
/* We do for queues that were marked with idle window flag. */
- if (cfq_cfqq_idle_window(cfqq))
+ if (cfq_cfqq_idle_window(cfqq) &&
+ !(blk_queue_nonrot(cfqd->queue) && cfqd->hw_tag))
return true;
/*
}
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_group *cfqg, enum wl_prio_t prio)
{
struct cfq_queue *queue;
int i;
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));
+ for (i = 0; i <= SYNC_WORKLOAD; ++i) {
+ /* select the one with lowest rb_key */
+ queue = cfq_rb_first(service_tree_for(cfqg, prio, i));
if (queue &&
(!key_valid || time_before(queue->rb_key, lowest_key))) {
lowest_key = queue->rb_key;
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;
* (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);
+ st = service_tree_for(cfqg, cfqd->serving_prio, cfqd->serving_type);
count = st->count;
/*
- * If priority didn't change, check workload expiration,
- * and that we still have other queues ready
+ * check workload expiration, and that we still have other queues ready
*/
- if (!prio_changed && count &&
- !time_after(jiffies, cfqd->workload_expires))
+ if (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);
+ cfq_choose_wl(cfqd, cfqg, cfqd->serving_prio);
+ st = service_tree_for(cfqg, cfqd->serving_prio, cfqd->serving_type);
count = st->count;
/*
cfqd->workload_expires = jiffies + cfqg->saved_workload_slice;
cfqd->serving_type = cfqg->saved_workload;
cfqd->serving_prio = cfqg->saved_serving_prio;
- }
+ } else
+ cfqd->workload_expires = jiffies - 1;
+
choose_service_tree(cfqd, cfqg);
}
if (!cfqd->rq_queued)
return NULL;
+
/*
- * The active queue has run out of time, expire it and select new.
+ * We were waiting for group to get backlogged. Expire the queue
*/
- if ((cfq_slice_used(cfqq) || cfq_cfqq_wait_busy_done(cfqq))
- && !cfq_cfqq_must_dispatch(cfqq))
+ if (cfq_cfqq_wait_busy(cfqq) && !RB_EMPTY_ROOT(&cfqq->sort_list))
goto expire;
/*
+ * The active queue has run out of time, expire it and select new.
+ */
+ if (cfq_slice_used(cfqq) && !cfq_cfqq_must_dispatch(cfqq)) {
+ /*
+ * If slice had not expired at the completion of last request
+ * we might not have turned on wait_busy flag. Don't expire
+ * the queue yet. Allow the group to get backlogged.
+ *
+ * The very fact that we have used the slice, that means we
+ * have been idling all along on this queue and it should be
+ * ok to wait for this request to complete.
+ */
+ if (cfqq->cfqg->nr_cfqq == 1 && RB_EMPTY_ROOT(&cfqq->sort_list)
+ && cfqq->dispatched && cfq_should_idle(cfqd, cfqq)) {
+ cfqq = NULL;
+ goto keep_queue;
+ } else
+ goto expire;
+ }
+
+ /*
* The active queue has requests and isn't expired, allow it to
* dispatch.
*/
* based on the last sync IO we serviced
*/
if (!cfq_cfqq_sync(cfqq) && cfqd->cfq_latency) {
- unsigned long last_sync = jiffies - cfqd->last_end_sync_rq;
+ unsigned long last_sync = jiffies - cfqd->last_delayed_sync;
unsigned int depth;
depth = last_sync / cfqd->cfq_slice[1];
static void cfq_put_queue(struct cfq_queue *cfqq)
{
struct cfq_data *cfqd = cfqq->cfqd;
- struct cfq_group *cfqg;
+ struct cfq_group *cfqg, *orig_cfqg;
BUG_ON(atomic_read(&cfqq->ref) <= 0);
BUG_ON(rb_first(&cfqq->sort_list));
BUG_ON(cfqq->allocated[READ] + cfqq->allocated[WRITE]);
cfqg = cfqq->cfqg;
+ orig_cfqg = cfqq->orig_cfqg;
if (unlikely(cfqd->active_queue == cfqq)) {
__cfq_slice_expired(cfqd, cfqq, 0);
BUG_ON(cfq_cfqq_on_rr(cfqq));
kmem_cache_free(cfq_pool, cfqq);
cfq_put_cfqg(cfqg);
+ if (orig_cfqg)
+ cfq_put_cfqg(orig_cfqg);
}
/*
return true;
/*
+ * Don't allow a non-RT request to preempt an ongoing RT cfqq timeslice.
+ */
+ if (cfq_class_rt(cfqq) && !cfq_class_rt(new_cfqq))
+ return false;
+
+ /*
* if the new request is sync, but the currently running queue is
* not, let the sync request have priority.
*/
* if this request is as-good as one we would expect from the
* current cfqq, let it preempt
*/
- if (cfq_rq_close(cfqd, cfqq, rq))
+ if (cfq_rq_close(cfqd, cfqq, rq, true))
return true;
return false;
cfqq->last_request_pos = blk_rq_pos(rq) + blk_rq_sectors(rq);
if (cfqq == cfqd->active_queue) {
- if (cfq_cfqq_wait_busy(cfqq)) {
- cfq_clear_cfqq_wait_busy(cfqq);
- cfq_mark_cfqq_wait_busy_done(cfqq);
- }
/*
* Remember that we saw a request from this process, but
* don't start queuing just yet. Otherwise we risk seeing lots
if (blk_rq_bytes(rq) > PAGE_CACHE_SIZE ||
cfqd->busy_queues > 1) {
del_timer(&cfqd->idle_slice_timer);
+ cfq_clear_cfqq_wait_request(cfqq);
__blk_run_queue(cfqd->queue);
} else
cfq_mark_cfqq_must_dispatch(cfqq);
cfqd->hw_tag = 0;
}
+static bool cfq_should_wait_busy(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+{
+ struct cfq_io_context *cic = cfqd->active_cic;
+
+ /* If there are other queues in the group, don't wait */
+ if (cfqq->cfqg->nr_cfqq > 1)
+ return false;
+
+ if (cfq_slice_used(cfqq))
+ return true;
+
+ /* if slice left is less than think time, wait busy */
+ if (cic && sample_valid(cic->ttime_samples)
+ && (cfqq->slice_end - jiffies < cic->ttime_mean))
+ return true;
+
+ /*
+ * If think times is less than a jiffy than ttime_mean=0 and above
+ * will not be true. It might happen that slice has not expired yet
+ * but will expire soon (4-5 ns) during select_queue(). To cover the
+ * 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)
+ return true;
+
+ return false;
+}
+
static void cfq_completed_request(struct request_queue *q, struct request *rq)
{
struct cfq_queue *cfqq = RQ_CFQQ(rq);
if (sync) {
RQ_CIC(rq)->last_end_request = now;
- cfqd->last_end_sync_rq = now;
+ if (!time_after(rq->start_time + cfqd->cfq_fifo_expire[1], now))
+ cfqd->last_delayed_sync = now;
}
/*
}
/*
- * If this queue consumed its slice and this is last queue
- * in the group, wait for next request before we expire
- * the queue
+ * Should we wait for next request to come in before we expire
+ * the queue.
*/
- if (cfq_slice_used(cfqq) && cfqq->cfqg->nr_cfqq == 1) {
+ if (cfq_should_wait_busy(cfqd, cfqq)) {
cfqq->slice_end = jiffies + cfqd->cfq_slice_idle;
cfq_mark_cfqq_wait_busy(cfqq);
}
* only if we processed at least one !rq_noidle request
*/
if (cfqd->serving_type == SYNC_WORKLOAD
- || cfqd->noidle_tree_requires_idle)
+ || cfqd->noidle_tree_requires_idle
+ || cfqq->cfqg->nr_cfqq == 1)
cfq_arm_slice_timer(cfqd);
}
}
cfq_put_queue(cfqd->async_idle_cfqq);
}
+static void cfq_cfqd_free(struct rcu_head *head)
+{
+ kfree(container_of(head, struct cfq_data, rcu));
+}
+
static void cfq_exit_queue(struct elevator_queue *e)
{
struct cfq_data *cfqd = e->elevator_data;
cfq_shutdown_timer_wq(cfqd);
/* Wait for cfqg->blkg->key accessors to exit their grace periods. */
- synchronize_rcu();
- kfree(cfqd);
+ call_rcu(&cfqd->rcu, cfq_cfqd_free);
}
static void *cfq_init_queue(struct request_queue *q)
cfqd->cfq_slice_async_rq = cfq_slice_async_rq;
cfqd->cfq_slice_idle = cfq_slice_idle;
cfqd->cfq_latency = 1;
+ cfqd->cfq_group_isolation = 0;
cfqd->hw_tag = -1;
- cfqd->last_end_sync_rq = jiffies;
+ /*
+ * 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;
+ INIT_RCU_HEAD(&cfqd->rcu);
return cfqd;
}
SHOW_FUNCTION(cfq_slice_async_show, cfqd->cfq_slice[0], 1);
SHOW_FUNCTION(cfq_slice_async_rq_show, cfqd->cfq_slice_async_rq, 0);
SHOW_FUNCTION(cfq_low_latency_show, cfqd->cfq_latency, 0);
+SHOW_FUNCTION(cfq_group_isolation_show, cfqd->cfq_group_isolation, 0);
#undef SHOW_FUNCTION
#define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV) \
STORE_FUNCTION(cfq_slice_async_rq_store, &cfqd->cfq_slice_async_rq, 1,
UINT_MAX, 0);
STORE_FUNCTION(cfq_low_latency_store, &cfqd->cfq_latency, 0, 1, 0);
+STORE_FUNCTION(cfq_group_isolation_store, &cfqd->cfq_group_isolation, 0, 1, 0);
#undef STORE_FUNCTION
#define CFQ_ATTR(name) \
CFQ_ATTR(slice_async_rq),
CFQ_ATTR(slice_idle),
CFQ_ATTR(low_latency),
+ CFQ_ATTR(group_isolation),
__ATTR_NULL
};
.elevator_owner = THIS_MODULE,
};
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
+static struct blkio_policy_type blkio_policy_cfq = {
+ .ops = {
+ .blkio_unlink_group_fn = cfq_unlink_blkio_group,
+ .blkio_update_group_weight_fn = cfq_update_blkio_group_weight,
+ },
+};
+#else
+static struct blkio_policy_type blkio_policy_cfq;
+#endif
+
static int __init cfq_init(void)
{
/*
return -ENOMEM;
elv_register(&iosched_cfq);
+ blkio_policy_register(&blkio_policy_cfq);
return 0;
}
static void __exit cfq_exit(void)
{
DECLARE_COMPLETION_ONSTACK(all_gone);
+ blkio_policy_unregister(&blkio_policy_cfq);
elv_unregister(&iosched_cfq);
ioc_gone = &all_gone;
/* ioc_gone's update must be visible before reading ioc_count */
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff