X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=block%2Fcfq-iosched.c;h=9c4b679908f41cf034cdddc79a9bff8bcb1f4e85;hb=0d9c778978ff268228c095ae737c282c03a5986d;hp=0ebb626a25d3ccdb13fed65093e96a48dbf69d9b;hpb=7b679138b3237a9a3d45a4fda23a58ac79cd279c;p=safe%2Fjmp%2Flinux-2.6 diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index 0ebb626..9c4b679 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -39,6 +39,7 @@ static int cfq_slice_idle = HZ / 125; #define CFQ_MIN_TT (2) #define CFQ_SLICE_SCALE (5) +#define CFQ_HW_QUEUE_MIN (5) #define RQ_CIC(rq) \ ((struct cfq_io_context *) (rq)->elevator_private) @@ -47,7 +48,7 @@ static int cfq_slice_idle = HZ / 125; static struct kmem_cache *cfq_pool; static struct kmem_cache *cfq_ioc_pool; -static DEFINE_PER_CPU(unsigned long, ioc_count); +static DEFINE_PER_CPU(unsigned long, cfq_ioc_count); static struct completion *ioc_gone; static DEFINE_SPINLOCK(ioc_gone_lock); @@ -55,9 +56,6 @@ static DEFINE_SPINLOCK(ioc_gone_lock); #define cfq_class_idle(cfqq) ((cfqq)->ioprio_class == IOPRIO_CLASS_IDLE) #define cfq_class_rt(cfqq) ((cfqq)->ioprio_class == IOPRIO_CLASS_RT) -#define ASYNC (0) -#define SYNC (1) - #define sample_valid(samples) ((samples) > 80) /* @@ -73,6 +71,51 @@ struct cfq_rb_root { #define CFQ_RB_ROOT (struct cfq_rb_root) { RB_ROOT, NULL, } /* + * Per process-grouping structure + */ +struct cfq_queue { + /* reference count */ + atomic_t ref; + /* various state flags, see below */ + unsigned int flags; + /* parent cfq_data */ + struct cfq_data *cfqd; + /* service_tree member */ + struct rb_node rb_node; + /* service_tree key */ + unsigned long rb_key; + /* prio tree member */ + struct rb_node p_node; + /* prio tree root we belong to, if any */ + struct rb_root *p_root; + /* sorted list of pending requests */ + struct rb_root sort_list; + /* if fifo isn't expired, next request to serve */ + struct request *next_rq; + /* requests queued in sort_list */ + int queued[2]; + /* currently allocated requests */ + int allocated[2]; + /* fifo list of requests in sort_list */ + struct list_head fifo; + + unsigned long slice_end; + long slice_resid; + unsigned int slice_dispatch; + + /* pending metadata requests */ + int meta_pending; + /* number of requests that are on the dispatch list or inside driver */ + int dispatched; + + /* io prio of this group */ + unsigned short ioprio, org_ioprio; + unsigned short ioprio_class, org_ioprio_class; + + pid_t pid; +}; + +/* * Per block device queue structure */ struct cfq_data { @@ -82,17 +125,32 @@ struct cfq_data { * rr list of queues with requests and the count of them */ struct cfq_rb_root service_tree; + + /* + * Each priority tree is sorted by next_request position. These + * trees are used when determining if two or more queues are + * interleaving requests (see cfq_close_cooperator). + */ + struct rb_root prio_trees[CFQ_PRIO_LISTS]; + unsigned int busy_queues; - int rq_in_driver; + int rq_in_driver[2]; int sync_flight; + + /* + * queue-depth detection + */ + int rq_queued; int hw_tag; + int hw_tag_samples; + int rq_in_driver_peak; /* * idle window management */ struct timer_list idle_slice_timer; - struct work_struct unplug_work; + struct delayed_work unplug_work; struct cfq_queue *active_queue; struct cfq_io_context *active_cic; @@ -104,7 +162,6 @@ struct cfq_data { struct cfq_queue *async_idle_cfqq; sector_t last_position; - unsigned long last_end_request; /* * tunables, see top of file @@ -116,62 +173,29 @@ struct cfq_data { unsigned int cfq_slice[2]; unsigned int cfq_slice_async_rq; unsigned int cfq_slice_idle; + unsigned int cfq_latency; struct list_head cic_list; -}; -/* - * Per process-grouping structure - */ -struct cfq_queue { - /* reference count */ - atomic_t ref; - /* various state flags, see below */ - unsigned int flags; - /* parent cfq_data */ - struct cfq_data *cfqd; - /* service_tree member */ - struct rb_node rb_node; - /* service_tree key */ - unsigned long rb_key; - /* sorted list of pending requests */ - struct rb_root sort_list; - /* if fifo isn't expired, next request to serve */ - struct request *next_rq; - /* requests queued in sort_list */ - int queued[2]; - /* currently allocated requests */ - int allocated[2]; - /* fifo list of requests in sort_list */ - struct list_head fifo; - - unsigned long slice_end; - long slice_resid; - - /* pending metadata requests */ - int meta_pending; - /* number of requests that are on the dispatch list or inside driver */ - int dispatched; - - /* io prio of this group */ - unsigned short ioprio, org_ioprio; - unsigned short ioprio_class, org_ioprio_class; + /* + * Fallback dummy cfqq for extreme OOM conditions + */ + struct cfq_queue oom_cfqq; - pid_t pid; + unsigned long last_end_sync_rq; }; enum cfqq_state_flags { CFQ_CFQQ_FLAG_on_rr = 0, /* on round-robin busy list */ CFQ_CFQQ_FLAG_wait_request, /* waiting for a request */ - CFQ_CFQQ_FLAG_must_alloc, /* must be allowed rq alloc */ + CFQ_CFQQ_FLAG_must_dispatch, /* must be allowed a dispatch */ CFQ_CFQQ_FLAG_must_alloc_slice, /* per-slice must_alloc flag */ - CFQ_CFQQ_FLAG_must_dispatch, /* must dispatch, even if expired */ CFQ_CFQQ_FLAG_fifo_expire, /* FIFO checked in this slice */ CFQ_CFQQ_FLAG_idle_window, /* slice idling enabled */ CFQ_CFQQ_FLAG_prio_changed, /* task priority has changed */ - CFQ_CFQQ_FLAG_queue_new, /* queue never been serviced */ 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 */ }; #define CFQ_CFQQ_FNS(name) \ @@ -190,15 +214,14 @@ static inline int cfq_cfqq_##name(const struct cfq_queue *cfqq) \ CFQ_CFQQ_FNS(on_rr); CFQ_CFQQ_FNS(wait_request); -CFQ_CFQQ_FNS(must_alloc); -CFQ_CFQQ_FNS(must_alloc_slice); CFQ_CFQQ_FNS(must_dispatch); +CFQ_CFQQ_FNS(must_alloc_slice); CFQ_CFQQ_FNS(fifo_expire); CFQ_CFQQ_FNS(idle_window); CFQ_CFQQ_FNS(prio_changed); -CFQ_CFQQ_FNS(queue_new); CFQ_CFQQ_FNS(slice_new); CFQ_CFQQ_FNS(sync); +CFQ_CFQQ_FNS(coop); #undef CFQ_CFQQ_FNS #define cfq_log_cfqq(cfqd, cfqq, fmt, args...) \ @@ -212,6 +235,11 @@ static struct cfq_queue *cfq_get_queue(struct cfq_data *, int, static struct cfq_io_context *cfq_cic_lookup(struct cfq_data *, struct io_context *); +static inline int rq_in_driver(struct cfq_data *cfqd) +{ + return cfqd->rq_in_driver[0] + cfqd->rq_in_driver[1]; +} + static inline struct cfq_queue *cic_to_cfqq(struct cfq_io_context *cic, int is_sync) { @@ -230,7 +258,7 @@ static inline void cic_set_cfqq(struct cfq_io_context *cic, */ static inline int cfq_bio_sync(struct bio *bio) { - if (bio_data_dir(bio) == READ || bio_sync(bio)) + if (bio_data_dir(bio) == READ || bio_rw_flagged(bio, BIO_RW_SYNCIO)) return 1; return 0; @@ -240,11 +268,13 @@ static inline int cfq_bio_sync(struct bio *bio) * scheduler run of queue, if there are requests pending and no one in the * driver that will restart queueing */ -static inline void cfq_schedule_dispatch(struct cfq_data *cfqd) +static inline void cfq_schedule_dispatch(struct cfq_data *cfqd, + unsigned long delay) { if (cfqd->busy_queues) { cfq_log(cfqd, "schedule dispatch"); - kblockd_schedule_work(&cfqd->unplug_work); + kblockd_schedule_delayed_work(cfqd->queue, &cfqd->unplug_work, + delay); } } @@ -326,8 +356,8 @@ cfq_choose_req(struct cfq_data *cfqd, struct request *rq1, struct request *rq2) else if (rq_is_meta(rq2) && !rq_is_meta(rq1)) return rq2; - s1 = rq1->sector; - s2 = rq2->sector; + s1 = blk_rq_pos(rq1); + s2 = blk_rq_pos(rq2); last = cfqd->last_position; @@ -407,13 +437,17 @@ static struct cfq_queue *cfq_rb_first(struct cfq_rb_root *root) return NULL; } +static void rb_erase_init(struct rb_node *n, struct rb_root *root) +{ + rb_erase(n, root); + RB_CLEAR_NODE(n); +} + static void cfq_rb_erase(struct rb_node *n, struct cfq_rb_root *root) { if (root->left == n) root->left = NULL; - - rb_erase(n, &root->rb); - RB_CLEAR_NODE(n); + rb_erase_init(n, &root->rb); } /* @@ -458,8 +492,8 @@ static unsigned long cfq_slice_offset(struct cfq_data *cfqd, * requests waiting to be processed. It is sorted in the order that * we will service the queues. */ -static void cfq_service_tree_add(struct cfq_data *cfqd, - struct cfq_queue *cfqq, int add_front) +static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq, + int add_front) { struct rb_node **p, *parent; struct cfq_queue *__cfqq; @@ -532,6 +566,67 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, rb_insert_color(&cfqq->rb_node, &cfqd->service_tree.rb); } +static struct cfq_queue * +cfq_prio_tree_lookup(struct cfq_data *cfqd, struct rb_root *root, + sector_t sector, struct rb_node **ret_parent, + struct rb_node ***rb_link) +{ + struct rb_node **p, *parent; + struct cfq_queue *cfqq = NULL; + + parent = NULL; + p = &root->rb_node; + while (*p) { + struct rb_node **n; + + parent = *p; + cfqq = rb_entry(parent, struct cfq_queue, p_node); + + /* + * Sort strictly based on sector. Smallest to the left, + * largest to the right. + */ + if (sector > blk_rq_pos(cfqq->next_rq)) + n = &(*p)->rb_right; + else if (sector < blk_rq_pos(cfqq->next_rq)) + n = &(*p)->rb_left; + else + break; + p = n; + cfqq = NULL; + } + + *ret_parent = parent; + if (rb_link) + *rb_link = p; + return cfqq; +} + +static void cfq_prio_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq) +{ + struct rb_node **p, *parent; + struct cfq_queue *__cfqq; + + if (cfqq->p_root) { + rb_erase(&cfqq->p_node, cfqq->p_root); + cfqq->p_root = NULL; + } + + if (cfq_class_idle(cfqq)) + return; + if (!cfqq->next_rq) + return; + + cfqq->p_root = &cfqd->prio_trees[cfqq->org_ioprio]; + __cfqq = cfq_prio_tree_lookup(cfqd, cfqq->p_root, + blk_rq_pos(cfqq->next_rq), &parent, &p); + if (!__cfqq) { + rb_link_node(&cfqq->p_node, parent, p); + rb_insert_color(&cfqq->p_node, cfqq->p_root); + } else + cfqq->p_root = NULL; +} + /* * Update cfqq's position in the service tree. */ @@ -540,8 +635,10 @@ static void cfq_resort_rr_list(struct cfq_data *cfqd, struct cfq_queue *cfqq) /* * Resorting requires the cfqq to be on the RR list already. */ - if (cfq_cfqq_on_rr(cfqq)) + if (cfq_cfqq_on_rr(cfqq)) { cfq_service_tree_add(cfqd, cfqq, 0); + cfq_prio_tree_add(cfqd, cfqq); + } } /* @@ -570,6 +667,10 @@ static void cfq_del_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq) if (!RB_EMPTY_NODE(&cfqq->rb_node)) cfq_rb_erase(&cfqq->rb_node, &cfqd->service_tree); + if (cfqq->p_root) { + rb_erase(&cfqq->p_node, cfqq->p_root); + cfqq->p_root = NULL; + } BUG_ON(!cfqd->busy_queues); cfqd->busy_queues--; @@ -597,7 +698,7 @@ static void cfq_add_rq_rb(struct request *rq) { struct cfq_queue *cfqq = RQ_CFQQ(rq); struct cfq_data *cfqd = cfqq->cfqd; - struct request *__alias; + struct request *__alias, *prev; cfqq->queued[rq_is_sync(rq)]++; @@ -614,7 +715,15 @@ 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); + + /* + * adjust priority tree position, if ->next_rq changes + */ + if (prev != cfqq->next_rq) + cfq_prio_tree_add(cfqd, cfqq); + BUG_ON(!cfqq->next_rq); } @@ -650,30 +759,22 @@ static void cfq_activate_request(struct request_queue *q, struct request *rq) { struct cfq_data *cfqd = q->elevator->elevator_data; - cfqd->rq_in_driver++; + cfqd->rq_in_driver[rq_is_sync(rq)]++; cfq_log_cfqq(cfqd, RQ_CFQQ(rq), "activate rq, drv=%d", - cfqd->rq_in_driver); - - /* - * If the depth is larger 1, it really could be queueing. But lets - * make the mark a little higher - idling could still be good for - * low queueing, and a low queueing number could also just indicate - * a SCSI mid layer like behaviour where limit+1 is often seen. - */ - if (!cfqd->hw_tag && cfqd->rq_in_driver > 4) - cfqd->hw_tag = 1; + rq_in_driver(cfqd)); - cfqd->last_position = rq->hard_sector + rq->hard_nr_sectors; + cfqd->last_position = blk_rq_pos(rq) + blk_rq_sectors(rq); } static void cfq_deactivate_request(struct request_queue *q, struct request *rq) { struct cfq_data *cfqd = q->elevator->elevator_data; + const int sync = rq_is_sync(rq); - WARN_ON(!cfqd->rq_in_driver); - cfqd->rq_in_driver--; + WARN_ON(!cfqd->rq_in_driver[sync]); + cfqd->rq_in_driver[sync]--; cfq_log_cfqq(cfqd, RQ_CFQQ(rq), "deactivate rq, drv=%d", - cfqd->rq_in_driver); + rq_in_driver(cfqd)); } static void cfq_remove_request(struct request *rq) @@ -686,6 +787,7 @@ static void cfq_remove_request(struct request *rq) list_del_init(&rq->queuelist); cfq_del_rq_rb(rq); + cfqq->cfqd->rq_queued--; if (rq_is_meta(rq)) { WARN_ON(!cfqq->meta_pending); cfqq->meta_pending--; @@ -765,10 +867,15 @@ static void __cfq_set_active_queue(struct cfq_data *cfqd, if (cfqq) { cfq_log_cfqq(cfqd, cfqq, "set_active"); cfqq->slice_end = 0; + cfqq->slice_dispatch = 0; + + cfq_clear_cfqq_wait_request(cfqq); + cfq_clear_cfqq_must_dispatch(cfqq); cfq_clear_cfqq_must_alloc_slice(cfqq); cfq_clear_cfqq_fifo_expire(cfqq); cfq_mark_cfqq_slice_new(cfqq); - cfq_clear_cfqq_queue_new(cfqq); + + del_timer(&cfqd->idle_slice_timer); } cfqd->active_queue = cfqq; @@ -786,7 +893,6 @@ __cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq, if (cfq_cfqq_wait_request(cfqq)) del_timer(&cfqd->idle_slice_timer); - cfq_clear_cfqq_must_dispatch(cfqq); cfq_clear_cfqq_wait_request(cfqq); /* @@ -831,11 +937,15 @@ static struct cfq_queue *cfq_get_next_queue(struct cfq_data *cfqd) /* * Get and set a new active queue for service. */ -static struct cfq_queue *cfq_set_active_queue(struct cfq_data *cfqd) +static struct cfq_queue *cfq_set_active_queue(struct cfq_data *cfqd, + struct cfq_queue *cfqq) { - struct cfq_queue *cfqq; + if (!cfqq) { + cfqq = cfq_get_next_queue(cfqd); + if (cfqq) + cfq_clear_cfqq_coop(cfqq); + } - cfqq = cfq_get_next_queue(cfqd); __cfq_set_active_queue(cfqd, cfqq); return cfqq; } @@ -843,34 +953,106 @@ static struct cfq_queue *cfq_set_active_queue(struct cfq_data *cfqd) static inline sector_t cfq_dist_from_last(struct cfq_data *cfqd, struct request *rq) { - if (rq->sector >= cfqd->last_position) - return rq->sector - cfqd->last_position; + if (blk_rq_pos(rq) >= cfqd->last_position) + return blk_rq_pos(rq) - cfqd->last_position; else - return cfqd->last_position - rq->sector; + return cfqd->last_position - blk_rq_pos(rq); } +#define CIC_SEEK_THR 8 * 1024 +#define CIC_SEEKY(cic) ((cic)->seek_mean > CIC_SEEK_THR) + static inline int cfq_rq_close(struct cfq_data *cfqd, struct request *rq) { struct cfq_io_context *cic = cfqd->active_cic; + sector_t sdist = cic->seek_mean; if (!sample_valid(cic->seek_samples)) - return 0; + sdist = CIC_SEEK_THR; + + return cfq_dist_from_last(cfqd, rq) <= sdist; +} + +static struct cfq_queue *cfqq_close(struct cfq_data *cfqd, + struct cfq_queue *cur_cfqq) +{ + struct rb_root *root = &cfqd->prio_trees[cur_cfqq->org_ioprio]; + struct rb_node *parent, *node; + struct cfq_queue *__cfqq; + sector_t sector = cfqd->last_position; + + if (RB_EMPTY_ROOT(root)) + return NULL; + + /* + * First, if we find a request starting at the end of the last + * request, choose it. + */ + __cfqq = cfq_prio_tree_lookup(cfqd, root, sector, &parent, NULL); + if (__cfqq) + return __cfqq; + + /* + * If the exact sector wasn't found, the parent of the NULL leaf + * will contain the closest sector. + */ + __cfqq = rb_entry(parent, struct cfq_queue, p_node); + if (cfq_rq_close(cfqd, __cfqq->next_rq)) + return __cfqq; + + if (blk_rq_pos(__cfqq->next_rq) < sector) + node = rb_next(&__cfqq->p_node); + else + node = rb_prev(&__cfqq->p_node); + if (!node) + return NULL; + + __cfqq = rb_entry(node, struct cfq_queue, p_node); + if (cfq_rq_close(cfqd, __cfqq->next_rq)) + return __cfqq; - return cfq_dist_from_last(cfqd, rq) <= cic->seek_mean; + return NULL; } -static int cfq_close_cooperator(struct cfq_data *cfq_data, - struct cfq_queue *cfqq) +/* + * cfqd - obvious + * cur_cfqq - passed in so that we don't decide that the current queue is + * closely cooperating with itself. + * + * So, basically we're assuming that that cur_cfqq has dispatched at least + * one request, and that cfqd->last_position reflects a position on the disk + * associated with the I/O issued by cur_cfqq. I'm not sure this is a valid + * assumption. + */ +static struct cfq_queue *cfq_close_cooperator(struct cfq_data *cfqd, + struct cfq_queue *cur_cfqq, + int probe) { + struct cfq_queue *cfqq; + + /* + * A valid cfq_io_context is necessary to compare requests against + * the seek_mean of the current cfqq. + */ + if (!cfqd->active_cic) + 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 0; -} + cfqq = cfqq_close(cfqd, cur_cfqq); + if (!cfqq) + return NULL; + + if (cfq_cfqq_coop(cfqq)) + return NULL; -#define CIC_SEEKY(cic) ((cic)->seek_mean > (8 * 1024)) + if (!probe) + cfq_mark_cfqq_coop(cfqq); + return cfqq; +} static void cfq_arm_slice_timer(struct cfq_data *cfqd) { @@ -878,6 +1060,14 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd) struct cfq_io_context *cic; unsigned long sl; + /* + * SSD device without seek penalty, disable idling. But only do so + * for devices that support queuing, otherwise we still have a problem + * with sync vs async workloads. + */ + if (blk_queue_nonrot(cfqd->queue) && cfqd->hw_tag) + return; + WARN_ON(!RB_EMPTY_ROOT(&cfqq->sort_list)); WARN_ON(cfq_cfqq_slice_new(cfqq)); @@ -890,7 +1080,7 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd) /* * still requests with the driver, don't idle */ - if (cfqd->rq_in_driver) + if (rq_in_driver(cfqd)) return; /* @@ -900,14 +1090,6 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd) if (!cic || !atomic_read(&cic->ioc->nr_tasks)) return; - /* - * See if this prio level has a good candidate - */ - if (cfq_close_cooperator(cfqd, cfqq) && - (sample_valid(cic->ttime_samples) && cic->ttime_mean > 2)) - return; - - cfq_mark_cfqq_must_dispatch(cfqq); cfq_mark_cfqq_wait_request(cfqq); /* @@ -920,7 +1102,7 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd) sl = min(sl, msecs_to_jiffies(CFQ_MIN_TT)); mod_timer(&cfqd->idle_slice_timer, jiffies + sl); - cfq_log(cfqd, "arm_idle: %lu", sl); + cfq_log_cfqq(cfqd, cfqq, "arm_idle: %lu", sl); } /* @@ -933,6 +1115,7 @@ static void cfq_dispatch_insert(struct request_queue *q, struct request *rq) cfq_log_cfqq(cfqd, cfqq, "dispatch_insert"); + cfqq->next_rq = cfq_find_next_rq(cfqd, cfqq, rq); cfq_remove_request(rq); cfqq->dispatched++; elv_dispatch_sort(q, rq); @@ -984,7 +1167,7 @@ cfq_prio_to_maxrq(struct cfq_data *cfqd, struct cfq_queue *cfqq) */ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd) { - struct cfq_queue *cfqq; + struct cfq_queue *cfqq, *new_cfqq = NULL; cfqq = cfqd->active_queue; if (!cfqq) @@ -993,7 +1176,7 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd) /* * The active queue has run out of time, expire it and select new. */ - if (cfq_slice_used(cfqq)) + if (cfq_slice_used(cfqq) && !cfq_cfqq_must_dispatch(cfqq)) goto expire; /* @@ -1004,6 +1187,16 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd) goto keep_queue; /* + * If another queue has a request waiting within our mean seek + * distance, let it run. The expire code will check for close + * cooperators and put the close queue at the front of the service + * tree. + */ + new_cfqq = cfq_close_cooperator(cfqd, cfqq, 0); + if (new_cfqq) + goto expire; + + /* * No requests pending. If the active queue still has requests in * flight or is idling for a new request, allow either of these * conditions to happen (or time out) before selecting a new queue. @@ -1017,64 +1210,11 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd) expire: cfq_slice_expired(cfqd, 0); new_queue: - cfqq = cfq_set_active_queue(cfqd); + cfqq = cfq_set_active_queue(cfqd, new_cfqq); keep_queue: return cfqq; } -/* - * Dispatch some requests from cfqq, moving them to the request queue - * dispatch list. - */ -static int -__cfq_dispatch_requests(struct cfq_data *cfqd, struct cfq_queue *cfqq, - int max_dispatch) -{ - int dispatched = 0; - - BUG_ON(RB_EMPTY_ROOT(&cfqq->sort_list)); - - do { - struct request *rq; - - /* - * follow expired path, else get first next available - */ - rq = cfq_check_fifo(cfqq); - if (rq == NULL) - rq = cfqq->next_rq; - - /* - * finally, insert request into driver dispatch list - */ - cfq_dispatch_insert(cfqd->queue, rq); - - dispatched++; - - if (!cfqd->active_cic) { - atomic_inc(&RQ_CIC(rq)->ioc->refcount); - cfqd->active_cic = RQ_CIC(rq); - } - - if (RB_EMPTY_ROOT(&cfqq->sort_list)) - break; - - } while (dispatched < max_dispatch); - - /* - * expire an async queue immediately if it has used up its slice. idle - * queue always expire after 1 dispatch round. - */ - if (cfqd->busy_queues > 1 && ((!cfq_cfqq_sync(cfqq) && - dispatched >= cfq_prio_to_maxrq(cfqd, cfqq)) || - cfq_class_idle(cfqq))) { - cfqq->slice_end = jiffies + 1; - cfq_slice_expired(cfqd, 0); - } - - return dispatched; -} - static int __cfq_forced_dispatch_cfqq(struct cfq_queue *cfqq) { int dispatched = 0; @@ -1104,15 +1244,49 @@ static int cfq_forced_dispatch(struct cfq_data *cfqd) BUG_ON(cfqd->busy_queues); - cfq_log(cfqd, "forced_dispatch=%d\n", dispatched); + cfq_log(cfqd, "forced_dispatch=%d", dispatched); return dispatched; } +/* + * Dispatch a request from cfqq, moving them to the request queue + * dispatch list. + */ +static void cfq_dispatch_request(struct cfq_data *cfqd, struct cfq_queue *cfqq) +{ + struct request *rq; + + BUG_ON(RB_EMPTY_ROOT(&cfqq->sort_list)); + + /* + * follow expired path, else get first next available + */ + rq = cfq_check_fifo(cfqq); + if (!rq) + rq = cfqq->next_rq; + + /* + * insert request into driver dispatch list + */ + cfq_dispatch_insert(cfqd->queue, rq); + + if (!cfqd->active_cic) { + struct cfq_io_context *cic = RQ_CIC(rq); + + atomic_long_inc(&cic->ioc->refcount); + cfqd->active_cic = cic; + } +} + +/* + * Find the cfqq that we need to service and move a request from that to the + * dispatch list + */ static int cfq_dispatch_requests(struct request_queue *q, int force) { struct cfq_data *cfqd = q->elevator->elevator_data; struct cfq_queue *cfqq; - int dispatched; + unsigned int max_dispatch; if (!cfqd->busy_queues) return 0; @@ -1120,33 +1294,87 @@ static int cfq_dispatch_requests(struct request_queue *q, int force) if (unlikely(force)) return cfq_forced_dispatch(cfqd); - dispatched = 0; - while ((cfqq = cfq_select_queue(cfqd)) != NULL) { - int max_dispatch; + cfqq = cfq_select_queue(cfqd); + if (!cfqq) + return 0; + + /* + * Drain async requests before we start sync IO + */ + if (cfq_cfqq_idle_window(cfqq) && cfqd->rq_in_driver[BLK_RW_ASYNC]) + return 0; + + /* + * If this is an async queue and we have sync IO in flight, let it wait + */ + if (cfqd->sync_flight && !cfq_cfqq_sync(cfqq)) + return 0; + + max_dispatch = cfqd->cfq_quantum; + if (cfq_class_idle(cfqq)) + max_dispatch = 1; - max_dispatch = cfqd->cfq_quantum; + /* + * Does this cfqq already have too much IO in flight? + */ + if (cfqq->dispatched >= max_dispatch) { + /* + * idle queue must always only have a single IO in flight + */ if (cfq_class_idle(cfqq)) - max_dispatch = 1; + return 0; - if (cfqq->dispatched >= max_dispatch) { - if (cfqd->busy_queues > 1) - break; - if (cfqq->dispatched >= 4 * max_dispatch) - break; - } + /* + * We have other queues, don't allow more IO from this one + */ + if (cfqd->busy_queues > 1) + return 0; - if (cfqd->sync_flight && !cfq_cfqq_sync(cfqq)) - break; + /* + * Sole queue user, allow bigger slice + */ + max_dispatch *= 4; + } - cfq_clear_cfqq_must_dispatch(cfqq); - cfq_clear_cfqq_wait_request(cfqq); - del_timer(&cfqd->idle_slice_timer); + /* + * Async queues must wait a bit before being allowed dispatch. + * We also ramp up the dispatch depth gradually for async IO, + * 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 int depth; + + depth = last_sync / cfqd->cfq_slice[1]; + if (!depth && !cfqq->dispatched) + depth = 1; + if (depth < max_dispatch) + max_dispatch = depth; + } + + if (cfqq->dispatched >= max_dispatch) + return 0; + + /* + * Dispatch a request from this cfqq + */ + cfq_dispatch_request(cfqd, cfqq); + cfqq->slice_dispatch++; + cfq_clear_cfqq_must_dispatch(cfqq); - dispatched += __cfq_dispatch_requests(cfqd, cfqq, max_dispatch); + /* + * expire an async queue immediately if it has used up its slice. idle + * queue always expire after 1 dispatch round. + */ + 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; + cfq_slice_expired(cfqd, 0); } - cfq_log(cfqd, "dispatched=%d", dispatched); - return dispatched; + cfq_log_cfqq(cfqd, cfqq, "dispatched a request"); + return 1; } /* @@ -1171,7 +1399,7 @@ static void cfq_put_queue(struct cfq_queue *cfqq) if (unlikely(cfqd->active_queue == cfqq)) { __cfq_slice_expired(cfqd, cfqq, 0); - cfq_schedule_dispatch(cfqd); + cfq_schedule_dispatch(cfqd, 0); } kmem_cache_free(cfq_pool, cfqq); @@ -1210,7 +1438,7 @@ static void cfq_cic_free_rcu(struct rcu_head *head) cic = container_of(head, struct cfq_io_context, rcu_head); kmem_cache_free(cfq_ioc_pool, cic); - elv_ioc_count_dec(ioc_count); + elv_ioc_count_dec(cfq_ioc_count); if (ioc_gone) { /* @@ -1219,7 +1447,7 @@ static void cfq_cic_free_rcu(struct rcu_head *head) * complete ioc_gone and set it back to NULL */ spin_lock(&ioc_gone_lock); - if (ioc_gone && !elv_ioc_count_read(ioc_count)) { + if (ioc_gone && !elv_ioc_count_read(cfq_ioc_count)) { complete(ioc_gone); ioc_gone = NULL; } @@ -1266,7 +1494,7 @@ static void cfq_exit_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq) { if (unlikely(cfqq == cfqd->active_queue)) { __cfq_slice_expired(cfqd, cfqq, 0); - cfq_schedule_dispatch(cfqd); + cfq_schedule_dispatch(cfqd, 0); } cfq_put_queue(cfqq); @@ -1289,14 +1517,14 @@ static void __cfq_exit_single_io_context(struct cfq_data *cfqd, if (ioc->ioc_data == cic) rcu_assign_pointer(ioc->ioc_data, NULL); - if (cic->cfqq[ASYNC]) { - cfq_exit_cfqq(cfqd, cic->cfqq[ASYNC]); - cic->cfqq[ASYNC] = NULL; + if (cic->cfqq[BLK_RW_ASYNC]) { + cfq_exit_cfqq(cfqd, cic->cfqq[BLK_RW_ASYNC]); + cic->cfqq[BLK_RW_ASYNC] = NULL; } - if (cic->cfqq[SYNC]) { - cfq_exit_cfqq(cfqd, cic->cfqq[SYNC]); - cic->cfqq[SYNC] = NULL; + if (cic->cfqq[BLK_RW_SYNC]) { + cfq_exit_cfqq(cfqd, cic->cfqq[BLK_RW_SYNC]); + cic->cfqq[BLK_RW_SYNC] = NULL; } } @@ -1310,7 +1538,15 @@ static void cfq_exit_single_io_context(struct io_context *ioc, unsigned long flags; spin_lock_irqsave(q->queue_lock, flags); - __cfq_exit_single_io_context(cfqd, cic); + + /* + * Ensure we get a fresh copy of the ->key to prevent + * race between exiting task and queue + */ + smp_read_barrier_depends(); + if (cic->key) + __cfq_exit_single_io_context(cfqd, cic); + spin_unlock_irqrestore(q->queue_lock, flags); } } @@ -1337,7 +1573,7 @@ cfq_alloc_io_context(struct cfq_data *cfqd, gfp_t gfp_mask) INIT_HLIST_NODE(&cic->cic_list); cic->dtor = cfq_free_io_context; cic->exit = cfq_exit_io_context; - elv_ioc_count_inc(ioc_count); + elv_ioc_count_inc(cfq_ioc_count); } return cic; @@ -1397,17 +1633,18 @@ static void changed_ioprio(struct io_context *ioc, struct cfq_io_context *cic) spin_lock_irqsave(cfqd->queue->queue_lock, flags); - cfqq = cic->cfqq[ASYNC]; + cfqq = cic->cfqq[BLK_RW_ASYNC]; if (cfqq) { struct cfq_queue *new_cfqq; - new_cfqq = cfq_get_queue(cfqd, ASYNC, cic->ioc, GFP_ATOMIC); + new_cfqq = cfq_get_queue(cfqd, BLK_RW_ASYNC, cic->ioc, + GFP_ATOMIC); if (new_cfqq) { - cic->cfqq[ASYNC] = new_cfqq; + cic->cfqq[BLK_RW_ASYNC] = new_cfqq; cfq_put_queue(cfqq); } } - cfqq = cic->cfqq[SYNC]; + cfqq = cic->cfqq[BLK_RW_SYNC]; if (cfqq) cfq_mark_cfqq_prio_changed(cfqq); @@ -1420,6 +1657,26 @@ static void cfq_ioc_set_ioprio(struct io_context *ioc) ioc->ioprio_changed = 0; } +static void cfq_init_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq, + pid_t pid, int is_sync) +{ + RB_CLEAR_NODE(&cfqq->rb_node); + RB_CLEAR_NODE(&cfqq->p_node); + INIT_LIST_HEAD(&cfqq->fifo); + + atomic_set(&cfqq->ref, 0); + cfqq->cfqd = cfqd; + + cfq_mark_cfqq_prio_changed(cfqq); + + if (is_sync) { + if (!cfq_class_idle(cfqq)) + cfq_mark_cfqq_idle_window(cfqq); + cfq_mark_cfqq_sync(cfqq); + } + cfqq->pid = pid; +} + static struct cfq_queue * cfq_find_alloc_queue(struct cfq_data *cfqd, int is_sync, struct io_context *ioc, gfp_t gfp_mask) @@ -1432,56 +1689,40 @@ retry: /* cic always exists here */ cfqq = cic_to_cfqq(cic, is_sync); - if (!cfqq) { + /* + * Always try a new alloc if we fell back to the OOM cfqq + * originally, since it should just be a temporary situation. + */ + if (!cfqq || cfqq == &cfqd->oom_cfqq) { + cfqq = NULL; if (new_cfqq) { cfqq = new_cfqq; new_cfqq = NULL; } else if (gfp_mask & __GFP_WAIT) { - /* - * Inform the allocator of the fact that we will - * just repeat this allocation if it fails, to allow - * the allocator to do whatever it needs to attempt to - * free memory. - */ spin_unlock_irq(cfqd->queue->queue_lock); new_cfqq = kmem_cache_alloc_node(cfq_pool, - gfp_mask | __GFP_NOFAIL | __GFP_ZERO, + gfp_mask | __GFP_ZERO, cfqd->queue->node); spin_lock_irq(cfqd->queue->queue_lock); - goto retry; + if (new_cfqq) + goto retry; } else { cfqq = kmem_cache_alloc_node(cfq_pool, gfp_mask | __GFP_ZERO, cfqd->queue->node); - if (!cfqq) - goto out; } - RB_CLEAR_NODE(&cfqq->rb_node); - INIT_LIST_HEAD(&cfqq->fifo); - - atomic_set(&cfqq->ref, 0); - cfqq->cfqd = cfqd; - - cfq_mark_cfqq_prio_changed(cfqq); - cfq_mark_cfqq_queue_new(cfqq); - - cfq_init_prio_data(cfqq, ioc); - - if (is_sync) { - if (!cfq_class_idle(cfqq)) - cfq_mark_cfqq_idle_window(cfqq); - cfq_mark_cfqq_sync(cfqq); - } - cfqq->pid = current->pid; - cfq_log_cfqq(cfqd, cfqq, "alloced"); + if (cfqq) { + cfq_init_cfqq(cfqd, cfqq, current->pid, is_sync); + cfq_init_prio_data(cfqq, ioc); + cfq_log_cfqq(cfqd, cfqq, "alloced"); + } else + cfqq = &cfqd->oom_cfqq; } if (new_cfqq) kmem_cache_free(cfq_pool, new_cfqq); -out: - WARN_ON((gfp_mask & __GFP_WAIT) && !cfqq); return cfqq; } @@ -1514,11 +1755,8 @@ cfq_get_queue(struct cfq_data *cfqd, int is_sync, struct io_context *ioc, cfqq = *async_cfqq; } - if (!cfqq) { + if (!cfqq) cfqq = cfq_find_alloc_queue(cfqd, is_sync, ioc, gfp_mask); - if (!cfqq) - return NULL; - } /* * pin the queue now that it's allocated, scheduler exit will prune it @@ -1694,10 +1932,12 @@ cfq_update_io_seektime(struct cfq_data *cfqd, struct cfq_io_context *cic, sector_t sdist; u64 total; - if (cic->last_request_pos < rq->sector) - sdist = rq->sector - cic->last_request_pos; + if (!cic->last_request_pos) + sdist = 0; + else if (cic->last_request_pos < blk_rq_pos(rq)) + sdist = blk_rq_pos(rq) - cic->last_request_pos; else - sdist = cic->last_request_pos - rq->sector; + sdist = cic->last_request_pos - blk_rq_pos(rq); /* * Don't allow the seek distance to get too large from the @@ -1731,10 +1971,10 @@ cfq_update_idle_window(struct cfq_data *cfqd, struct cfq_queue *cfqq, if (!cfq_cfqq_sync(cfqq) || cfq_class_idle(cfqq)) return; - old_idle = cfq_cfqq_idle_window(cfqq); + enable_idle = old_idle = cfq_cfqq_idle_window(cfqq); if (!atomic_read(&cic->ioc->nr_tasks) || !cfqd->cfq_slice_idle || - (cfqd->hw_tag && CIC_SEEKY(cic))) + (!cfqd->cfq_latency && cfqd->hw_tag && CIC_SEEKY(cic))) enable_idle = 0; else if (sample_valid(cic->ttime_samples)) { if (cic->ttime_mean > cfqd->cfq_slice_idle) @@ -1789,6 +2029,12 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq, if (rq_is_meta(rq) && !cfqq->meta_pending) return 1; + /* + * Allow an RT request to pre-empt an ongoing non-RT cfqq timeslice. + */ + if (cfq_class_rt(new_cfqq) && !cfq_class_rt(cfqq)) + return 1; + if (!cfqd->active_cic || !cfq_cfqq_wait_request(cfqq)) return 0; @@ -1833,6 +2079,7 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq, { struct cfq_io_context *cic = RQ_CIC(rq); + cfqd->rq_queued++; if (rq_is_meta(rq)) cfqq->meta_pending++; @@ -1840,28 +2087,36 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq, cfq_update_io_seektime(cfqd, cic, rq); cfq_update_idle_window(cfqd, cfqq, cic); - cic->last_request_pos = rq->sector + rq->nr_sectors; + cic->last_request_pos = blk_rq_pos(rq) + blk_rq_sectors(rq); if (cfqq == cfqd->active_queue) { /* - * if we are waiting for a request for this queue, let it rip - * immediately and flag that we must not expire this queue - * just now + * Remember that we saw a request from this process, but + * don't start queuing just yet. Otherwise we risk seeing lots + * of tiny requests, because we disrupt the normal plugging + * and merging. If the request is already larger than a single + * page, let it rip immediately. For that case we assume that + * merging is already done. Ditto for a busy system that + * has other work pending, don't risk delaying until the + * idle timer unplug to continue working. */ if (cfq_cfqq_wait_request(cfqq)) { + if (blk_rq_bytes(rq) > PAGE_CACHE_SIZE || + cfqd->busy_queues > 1) { + del_timer(&cfqd->idle_slice_timer); + __blk_run_queue(cfqd->queue); + } cfq_mark_cfqq_must_dispatch(cfqq); - del_timer(&cfqd->idle_slice_timer); - blk_start_queueing(cfqd->queue); } } else if (cfq_should_preempt(cfqd, cfqq, rq)) { /* * not the active queue - expire current slice if it is * idle and has expired it's mean thinktime or this new queue - * has some old slice time left and is of higher priority + * has some old slice time left and is of higher priority or + * this new queue is RT and the current one is BE */ cfq_preempt_queue(cfqd, cfqq); - cfq_mark_cfqq_must_dispatch(cfqq); - blk_start_queueing(cfqd->queue); + __blk_run_queue(cfqd->queue); } } @@ -1880,6 +2135,31 @@ static void cfq_insert_request(struct request_queue *q, struct request *rq) cfq_rq_enqueued(cfqd, cfqq, rq); } +/* + * Update hw_tag based on peak queue depth over 50 samples under + * sufficient load. + */ +static void cfq_update_hw_tag(struct cfq_data *cfqd) +{ + if (rq_in_driver(cfqd) > cfqd->rq_in_driver_peak) + cfqd->rq_in_driver_peak = rq_in_driver(cfqd); + + if (cfqd->rq_queued <= CFQ_HW_QUEUE_MIN && + rq_in_driver(cfqd) <= CFQ_HW_QUEUE_MIN) + return; + + if (cfqd->hw_tag_samples++ < 50) + return; + + if (cfqd->rq_in_driver_peak >= CFQ_HW_QUEUE_MIN) + cfqd->hw_tag = 1; + else + cfqd->hw_tag = 0; + + cfqd->hw_tag_samples = 0; + cfqd->rq_in_driver_peak = 0; +} + static void cfq_completed_request(struct request_queue *q, struct request *rq) { struct cfq_queue *cfqq = RQ_CFQQ(rq); @@ -1890,37 +2170,48 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq) now = jiffies; cfq_log_cfqq(cfqd, cfqq, "complete"); - WARN_ON(!cfqd->rq_in_driver); + cfq_update_hw_tag(cfqd); + + WARN_ON(!cfqd->rq_in_driver[sync]); WARN_ON(!cfqq->dispatched); - cfqd->rq_in_driver--; + cfqd->rq_in_driver[sync]--; cfqq->dispatched--; if (cfq_cfqq_sync(cfqq)) cfqd->sync_flight--; - if (!cfq_class_idle(cfqq)) - cfqd->last_end_request = now; - - if (sync) + if (sync) { RQ_CIC(rq)->last_end_request = now; + cfqd->last_end_sync_rq = now; + } /* * If this is the active queue, check if it needs to be expired, * or if we want to idle in case it has no pending requests. */ if (cfqd->active_queue == cfqq) { + const bool cfqq_empty = RB_EMPTY_ROOT(&cfqq->sort_list); + if (cfq_cfqq_slice_new(cfqq)) { cfq_set_prio_slice(cfqd, cfqq); cfq_clear_cfqq_slice_new(cfqq); } + /* + * If there are no requests waiting in this queue, and + * there are other queues ready to issue requests, AND + * those other queues are issuing requests within our + * mean seek distance, give them a chance to run instead + * of idling. + */ if (cfq_slice_used(cfqq) || cfq_class_idle(cfqq)) cfq_slice_expired(cfqd, 1); - else if (sync && RB_EMPTY_ROOT(&cfqq->sort_list)) + else if (cfqq_empty && !cfq_close_cooperator(cfqd, cfqq, 1) && + sync && !rq_noidle(rq)) cfq_arm_slice_timer(cfqd); } - if (!cfqd->rq_in_driver) - cfq_schedule_dispatch(cfqd); + if (!rq_in_driver(cfqd)) + cfq_schedule_dispatch(cfqd, 0); } /* @@ -1951,8 +2242,7 @@ static void cfq_prio_boost(struct cfq_queue *cfqq) static inline int __cfq_may_queue(struct cfq_queue *cfqq) { - if ((cfq_cfqq_wait_request(cfqq) || cfq_cfqq_must_alloc(cfqq)) && - !cfq_cfqq_must_alloc_slice(cfqq)) { + if (cfq_cfqq_wait_request(cfqq) && !cfq_cfqq_must_alloc_slice(cfqq)) { cfq_mark_cfqq_must_alloc_slice(cfqq); return ELV_MQUEUE_MUST; } @@ -1977,7 +2267,7 @@ static int cfq_may_queue(struct request_queue *q, int rw) if (!cic) return ELV_MQUEUE_MAY; - cfqq = cic_to_cfqq(cic, rw & REQ_RW_SYNC); + cfqq = cic_to_cfqq(cic, rw_is_sync(rw)); if (cfqq) { cfq_init_prio_data(cfqq, cic->ioc); cfq_prio_boost(cfqq); @@ -2033,17 +2323,12 @@ cfq_set_request(struct request_queue *q, struct request *rq, gfp_t gfp_mask) goto queue_fail; cfqq = cic_to_cfqq(cic, is_sync); - if (!cfqq) { + if (!cfqq || cfqq == &cfqd->oom_cfqq) { cfqq = cfq_get_queue(cfqd, is_sync, cic->ioc, gfp_mask); - - if (!cfqq) - goto queue_fail; - cic_set_cfqq(cic, cfqq, is_sync); } cfqq->allocated[rw]++; - cfq_clear_cfqq_must_alloc(cfqq); atomic_inc(&cfqq->ref); spin_unlock_irqrestore(q->queue_lock, flags); @@ -2056,7 +2341,7 @@ queue_fail: if (cic) put_io_context(cic->ioc); - cfq_schedule_dispatch(cfqd); + cfq_schedule_dispatch(cfqd, 0); spin_unlock_irqrestore(q->queue_lock, flags); cfq_log(cfqd, "set_request fail"); return 1; @@ -2065,13 +2350,12 @@ queue_fail: static void cfq_kick_queue(struct work_struct *work) { struct cfq_data *cfqd = - container_of(work, struct cfq_data, unplug_work); + container_of(work, struct cfq_data, unplug_work.work); struct request_queue *q = cfqd->queue; - unsigned long flags; - spin_lock_irqsave(q->queue_lock, flags); - blk_start_queueing(q); - spin_unlock_irqrestore(q->queue_lock, flags); + spin_lock_irq(q->queue_lock); + __blk_run_queue(cfqd->queue); + spin_unlock_irq(q->queue_lock); } /* @@ -2093,6 +2377,12 @@ static void cfq_idle_slice_timer(unsigned long data) timed_out = 0; /* + * We saw a request before the queue expired, let it through + */ + if (cfq_cfqq_must_dispatch(cfqq)) + goto out_kick; + + /* * expired */ if (cfq_slice_used(cfqq)) @@ -2108,15 +2398,13 @@ static void cfq_idle_slice_timer(unsigned long data) /* * not expired and it has a request pending, let it dispatch */ - if (!RB_EMPTY_ROOT(&cfqq->sort_list)) { - cfq_mark_cfqq_must_dispatch(cfqq); + if (!RB_EMPTY_ROOT(&cfqq->sort_list)) goto out_kick; - } } expire: cfq_slice_expired(cfqd, timed_out); out_kick: - cfq_schedule_dispatch(cfqd); + cfq_schedule_dispatch(cfqd, 0); out_cont: spin_unlock_irqrestore(cfqd->queue->queue_lock, flags); } @@ -2124,7 +2412,7 @@ out_cont: static void cfq_shutdown_timer_wq(struct cfq_data *cfqd) { del_timer_sync(&cfqd->idle_slice_timer); - kblockd_flush_work(&cfqd->unplug_work); + cancel_delayed_work_sync(&cfqd->unplug_work); } static void cfq_put_async_queues(struct cfq_data *cfqd) @@ -2142,7 +2430,7 @@ static void cfq_put_async_queues(struct cfq_data *cfqd) cfq_put_queue(cfqd->async_idle_cfqq); } -static void cfq_exit_queue(elevator_t *e) +static void cfq_exit_queue(struct elevator_queue *e) { struct cfq_data *cfqd = e->elevator_data; struct request_queue *q = cfqd->queue; @@ -2174,12 +2462,30 @@ static void cfq_exit_queue(elevator_t *e) static void *cfq_init_queue(struct request_queue *q) { struct cfq_data *cfqd; + int i; cfqd = kmalloc_node(sizeof(*cfqd), GFP_KERNEL | __GFP_ZERO, q->node); if (!cfqd) return NULL; cfqd->service_tree = CFQ_RB_ROOT; + + /* + * Not strictly needed (since RB_ROOT just clears the node and we + * zeroed cfqd on alloc), but better be safe in case someone decides + * to add magic to the rb code + */ + for (i = 0; i < CFQ_PRIO_LISTS; i++) + cfqd->prio_trees[i] = RB_ROOT; + + /* + * Our fallback cfqq if cfq_find_alloc_queue() runs into OOM issues. + * Grab a permanent reference to it, so that the normal code flow + * will not attempt to free it. + */ + cfq_init_cfqq(cfqd, &cfqd->oom_cfqq, 1, 0); + atomic_inc(&cfqd->oom_cfqq.ref); + INIT_LIST_HEAD(&cfqd->cic_list); cfqd->queue = q; @@ -2188,9 +2494,8 @@ static void *cfq_init_queue(struct request_queue *q) cfqd->idle_slice_timer.function = cfq_idle_slice_timer; cfqd->idle_slice_timer.data = (unsigned long) cfqd; - INIT_WORK(&cfqd->unplug_work, cfq_kick_queue); + INIT_DELAYED_WORK(&cfqd->unplug_work, cfq_kick_queue); - cfqd->last_end_request = jiffies; cfqd->cfq_quantum = cfq_quantum; cfqd->cfq_fifo_expire[0] = cfq_fifo_expire[0]; cfqd->cfq_fifo_expire[1] = cfq_fifo_expire[1]; @@ -2200,7 +2505,9 @@ static void *cfq_init_queue(struct request_queue *q) cfqd->cfq_slice[1] = cfq_slice_sync; cfqd->cfq_slice_async_rq = cfq_slice_async_rq; cfqd->cfq_slice_idle = cfq_slice_idle; - + cfqd->cfq_latency = 1; + cfqd->hw_tag = 1; + cfqd->last_end_sync_rq = jiffies; return cfqd; } @@ -2251,7 +2558,7 @@ cfq_var_store(unsigned int *var, const char *page, size_t count) } #define SHOW_FUNCTION(__FUNC, __VAR, __CONV) \ -static ssize_t __FUNC(elevator_t *e, char *page) \ +static ssize_t __FUNC(struct elevator_queue *e, char *page) \ { \ struct cfq_data *cfqd = e->elevator_data; \ unsigned int __data = __VAR; \ @@ -2268,10 +2575,11 @@ SHOW_FUNCTION(cfq_slice_idle_show, cfqd->cfq_slice_idle, 1); SHOW_FUNCTION(cfq_slice_sync_show, cfqd->cfq_slice[1], 1); 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); #undef SHOW_FUNCTION #define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV) \ -static ssize_t __FUNC(elevator_t *e, const char *page, size_t count) \ +static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count) \ { \ struct cfq_data *cfqd = e->elevator_data; \ unsigned int __data; \ @@ -2299,6 +2607,7 @@ STORE_FUNCTION(cfq_slice_sync_store, &cfqd->cfq_slice[1], 1, UINT_MAX, 1); STORE_FUNCTION(cfq_slice_async_store, &cfqd->cfq_slice[0], 1, UINT_MAX, 1); 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); #undef STORE_FUNCTION #define CFQ_ATTR(name) \ @@ -2314,6 +2623,7 @@ static struct elv_fs_entry cfq_attrs[] = { CFQ_ATTR(slice_async), CFQ_ATTR(slice_async_rq), CFQ_ATTR(slice_idle), + CFQ_ATTR(low_latency), __ATTR_NULL }; @@ -2373,7 +2683,7 @@ static void __exit cfq_exit(void) * this also protects us from entering cfq_slab_kill() with * pending RCU callbacks */ - if (elv_ioc_count_read(ioc_count)) + if (elv_ioc_count_read(cfq_ioc_count)) wait_for_completion(&all_gone); cfq_slab_kill(); }