diff options
-rw-r--r-- | Documentation/cgroups/blkio-controller.txt | 124 | ||||
-rw-r--r-- | block/blk-cgroup.c | 727 | ||||
-rw-r--r-- | block/blk-cgroup.h | 167 | ||||
-rw-r--r-- | block/blk-core.c | 13 | ||||
-rw-r--r-- | block/cfq-iosched.c | 90 | ||||
-rw-r--r-- | block/elevator.c | 9 | ||||
-rw-r--r-- | include/linux/backing-dev.h | 3 | ||||
-rw-r--r-- | include/linux/blkdev.h | 38 | ||||
-rw-r--r-- | include/linux/elevator.h | 6 | ||||
-rw-r--r-- | include/linux/writeback.h | 4 | ||||
-rw-r--r-- | mm/page-writeback.c | 39 |
11 files changed, 1124 insertions, 96 deletions
diff --git a/Documentation/cgroups/blkio-controller.txt b/Documentation/cgroups/blkio-controller.txt index 630879c..d422b41 100644 --- a/Documentation/cgroups/blkio-controller.txt +++ b/Documentation/cgroups/blkio-controller.txt @@ -76,10 +76,38 @@ CONFIG_DEBUG_BLK_CGROUP Details of cgroup files ======================= - blkio.weight - - Specifies per cgroup weight. - + - Specifies per cgroup weight. This is default weight of the group + on all the devices until and unless overridden by per device rule. + (See blkio.weight_device). Currently allowed range of weights is from 100 to 1000. +- blkio.weight_device + - One can specify per cgroup per device rules using this interface. + These rules override the default value of group weight as specified + by blkio.weight. + + Following is the format. + + #echo dev_maj:dev_minor weight > /path/to/cgroup/blkio.weight_device + Configure weight=300 on /dev/sdb (8:16) in this cgroup + # echo 8:16 300 > blkio.weight_device + # cat blkio.weight_device + dev weight + 8:16 300 + + Configure weight=500 on /dev/sda (8:0) in this cgroup + # echo 8:0 500 > blkio.weight_device + # cat blkio.weight_device + dev weight + 8:0 500 + 8:16 300 + + Remove specific weight for /dev/sda in this cgroup + # echo 8:0 0 > blkio.weight_device + # cat blkio.weight_device + dev weight + 8:16 300 + - blkio.time - disk time allocated to cgroup per device in milliseconds. First two fields specify the major and minor number of the device and @@ -92,6 +120,94 @@ Details of cgroup files third field specifies the number of sectors transferred by the group to/from the device. +- blkio.io_service_bytes + - Number of bytes transferred to/from the disk by the group. These + are further divided by the type of operation - read or write, sync + or async. First two fields specify the major and minor number of the + device, third field specifies the operation type and the fourth field + specifies the number of bytes. + +- blkio.io_serviced + - Number of IOs completed to/from the disk by the group. These + are further divided by the type of operation - read or write, sync + or async. First two fields specify the major and minor number of the + device, third field specifies the operation type and the fourth field + specifies the number of IOs. + +- blkio.io_service_time + - Total amount of time between request dispatch and request completion + for the IOs done by this cgroup. This is in nanoseconds to make it + meaningful for flash devices too. For devices with queue depth of 1, + this time represents the actual service time. When queue_depth > 1, + that is no longer true as requests may be served out of order. This + may cause the service time for a given IO to include the service time + of multiple IOs when served out of order which may result in total + io_service_time > actual time elapsed. This time is further divided by + the type of operation - read or write, sync or async. First two fields + specify the major and minor number of the device, third field + specifies the operation type and the fourth field specifies the + io_service_time in ns. + +- blkio.io_wait_time + - Total amount of time the IOs for this cgroup spent waiting in the + scheduler queues for service. This can be greater than the total time + elapsed since it is cumulative io_wait_time for all IOs. It is not a + measure of total time the cgroup spent waiting but rather a measure of + the wait_time for its individual IOs. For devices with queue_depth > 1 + this metric does not include the time spent waiting for service once + the IO is dispatched to the device but till it actually gets serviced + (there might be a time lag here due to re-ordering of requests by the + device). This is in nanoseconds to make it meaningful for flash + devices too. This time is further divided by the type of operation - + read or write, sync or async. First two fields specify the major and + minor number of the device, third field specifies the operation type + and the fourth field specifies the io_wait_time in ns. + +- blkio.io_merged + - Total number of bios/requests merged into requests belonging to this + cgroup. This is further divided by the type of operation - read or + write, sync or async. + +- blkio.io_queued + - Total number of requests queued up at any given instant for this + cgroup. This is further divided by the type of operation - read or + write, sync or async. + +- blkio.avg_queue_size + - Debugging aid only enabled if CONFIG_DEBUG_CFQ_IOSCHED=y. + The average queue size for this cgroup over the entire time of this + cgroup's existence. Queue size samples are taken each time one of the + queues of this cgroup gets a timeslice. + +- blkio.group_wait_time + - Debugging aid only enabled if CONFIG_DEBUG_CFQ_IOSCHED=y. + This is the amount of time the cgroup had to wait since it became busy + (i.e., went from 0 to 1 request queued) to get a timeslice for one of + its queues. This is different from the io_wait_time which is the + cumulative total of the amount of time spent by each IO in that cgroup + waiting in the scheduler queue. This is in nanoseconds. If this is + read when the cgroup is in a waiting (for timeslice) state, the stat + will only report the group_wait_time accumulated till the last time it + got a timeslice and will not include the current delta. + +- blkio.empty_time + - Debugging aid only enabled if CONFIG_DEBUG_CFQ_IOSCHED=y. + This is the amount of time a cgroup spends without any pending + requests when not being served, i.e., it does not include any time + spent idling for one of the queues of the cgroup. This is in + nanoseconds. If this is read when the cgroup is in an empty state, + the stat will only report the empty_time accumulated till the last + time it had a pending request and will not include the current delta. + +- blkio.idle_time + - Debugging aid only enabled if CONFIG_DEBUG_CFQ_IOSCHED=y. + This is the amount of time spent by the IO scheduler idling for a + given cgroup in anticipation of a better request than the exising ones + from other queues/cgroups. This is in nanoseconds. If this is read + when the cgroup is in an idling state, the stat will only report the + idle_time accumulated till the last idle period and will not include + the current delta. + - blkio.dequeue - Debugging aid only enabled if CONFIG_DEBUG_CFQ_IOSCHED=y. This gives the statistics about how many a times a group was dequeued @@ -99,6 +215,10 @@ Details of cgroup files and minor number of the device and third field specifies the number of times a group was dequeued from a particular device. +- blkio.reset_stats + - Writing an int to this file will result in resetting all the stats + for that cgroup. + CFQ sysfs tunable ================= /sys/block/<disk>/queue/iosched/group_isolation diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 5fe03de..aa97cd4 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -15,8 +15,12 @@ #include <linux/kdev_t.h> #include <linux/module.h> #include <linux/err.h> +#include <linux/blkdev.h> #include <linux/slab.h> #include "blk-cgroup.h" +#include <linux/genhd.h> + +#define MAX_KEY_LEN 100 static DEFINE_SPINLOCK(blkio_list_lock); static LIST_HEAD(blkio_list); @@ -49,6 +53,32 @@ struct cgroup_subsys blkio_subsys = { }; EXPORT_SYMBOL_GPL(blkio_subsys); +static inline void blkio_policy_insert_node(struct blkio_cgroup *blkcg, + struct blkio_policy_node *pn) +{ + list_add(&pn->node, &blkcg->policy_list); +} + +/* Must be called with blkcg->lock held */ +static inline void blkio_policy_delete_node(struct blkio_policy_node *pn) +{ + list_del(&pn->node); +} + +/* Must be called with blkcg->lock held */ +static struct blkio_policy_node * +blkio_policy_search_node(const struct blkio_cgroup *blkcg, dev_t dev) +{ + struct blkio_policy_node *pn; + + list_for_each_entry(pn, &blkcg->policy_list, node) { + if (pn->dev == dev) + return pn; + } + + return NULL; +} + struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup) { return container_of(cgroup_subsys_state(cgroup, blkio_subsys_id), @@ -56,13 +86,262 @@ struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup) } EXPORT_SYMBOL_GPL(cgroup_to_blkio_cgroup); -void blkiocg_update_blkio_group_stats(struct blkio_group *blkg, - unsigned long time, unsigned long sectors) +void blkio_group_init(struct blkio_group *blkg) +{ + spin_lock_init(&blkg->stats_lock); +} +EXPORT_SYMBOL_GPL(blkio_group_init); + +/* + * Add to the appropriate stat variable depending on the request type. + * This should be called with the blkg->stats_lock held. + */ +static void blkio_add_stat(uint64_t *stat, uint64_t add, bool direction, + bool sync) +{ + if (direction) + stat[BLKIO_STAT_WRITE] += add; + else + stat[BLKIO_STAT_READ] += add; + if (sync) + stat[BLKIO_STAT_SYNC] += add; + else + stat[BLKIO_STAT_ASYNC] += add; +} + +/* + * Decrements the appropriate stat variable if non-zero depending on the + * request type. Panics on value being zero. + * This should be called with the blkg->stats_lock held. + */ +static void blkio_check_and_dec_stat(uint64_t *stat, bool direction, bool sync) +{ + if (direction) { + BUG_ON(stat[BLKIO_STAT_WRITE] == 0); + stat[BLKIO_STAT_WRITE]--; + } else { + BUG_ON(stat[BLKIO_STAT_READ] == 0); + stat[BLKIO_STAT_READ]--; + } + if (sync) { + BUG_ON(stat[BLKIO_STAT_SYNC] == 0); + stat[BLKIO_STAT_SYNC]--; + } else { + BUG_ON(stat[BLKIO_STAT_ASYNC] == 0); + stat[BLKIO_STAT_ASYNC]--; + } +} + +#ifdef CONFIG_DEBUG_BLK_CGROUP +/* This should be called with the blkg->stats_lock held. */ +static void blkio_set_start_group_wait_time(struct blkio_group *blkg, + struct blkio_group *curr_blkg) +{ + if (blkio_blkg_waiting(&blkg->stats)) + return; + if (blkg == curr_blkg) + return; + blkg->stats.start_group_wait_time = sched_clock(); + blkio_mark_blkg_waiting(&blkg->stats); +} + +/* This should be called with the blkg->stats_lock held. */ +static void blkio_update_group_wait_time(struct blkio_group_stats *stats) +{ + unsigned long long now; + + if (!blkio_blkg_waiting(stats)) + return; + + now = sched_clock(); + if (time_after64(now, stats->start_group_wait_time)) + stats->group_wait_time += now - stats->start_group_wait_time; + blkio_clear_blkg_waiting(stats); +} + +/* This should be called with the blkg->stats_lock held. */ +static void blkio_end_empty_time(struct blkio_group_stats *stats) +{ + unsigned long long now; + + if (!blkio_blkg_empty(stats)) + return; + + now = sched_clock(); + if (time_after64(now, stats->start_empty_time)) + stats->empty_time += now - stats->start_empty_time; + blkio_clear_blkg_empty(stats); +} + +void blkiocg_update_set_idle_time_stats(struct blkio_group *blkg) +{ + unsigned long flags; + + spin_lock_irqsave(&blkg->stats_lock, flags); + BUG_ON(blkio_blkg_idling(&blkg->stats)); + blkg->stats.start_idle_time = sched_clock(); + blkio_mark_blkg_idling(&blkg->stats); + spin_unlock_irqrestore(&blkg->stats_lock, flags); +} +EXPORT_SYMBOL_GPL(blkiocg_update_set_idle_time_stats); + +void blkiocg_update_idle_time_stats(struct blkio_group *blkg) { - blkg->time += time; - blkg->sectors += sectors; + unsigned long flags; + unsigned long long now; + struct blkio_group_stats *stats; + + spin_lock_irqsave(&blkg->stats_lock, flags); + stats = &blkg->stats; + if (blkio_blkg_idling(stats)) { + now = sched_clock(); + if (time_after64(now, stats->start_idle_time)) + stats->idle_time += now - stats->start_idle_time; + blkio_clear_blkg_idling(stats); + } + spin_unlock_irqrestore(&blkg->stats_lock, flags); +} +EXPORT_SYMBOL_GPL(blkiocg_update_idle_time_stats); + +void blkiocg_update_avg_queue_size_stats(struct blkio_group *blkg) +{ + unsigned long flags; + struct blkio_group_stats *stats; + + spin_lock_irqsave(&blkg->stats_lock, flags); + stats = &blkg->stats; + stats->avg_queue_size_sum += + stats->stat_arr[BLKIO_STAT_QUEUED][BLKIO_STAT_READ] + + stats->stat_arr[BLKIO_STAT_QUEUED][BLKIO_STAT_WRITE]; + stats->avg_queue_size_samples++; + blkio_update_group_wait_time(stats); + spin_unlock_irqrestore(&blkg->stats_lock, flags); } -EXPORT_SYMBOL_GPL(blkiocg_update_blkio_group_stats); +EXPORT_SYMBOL_GPL(blkiocg_update_avg_queue_size_stats); + +void blkiocg_update_dequeue_stats(struct blkio_group *blkg, + unsigned long dequeue) +{ + blkg->stats.dequeue += dequeue; +} +EXPORT_SYMBOL_GPL(blkiocg_update_dequeue_stats); +#else +static inline void blkio_set_start_group_wait_time(struct blkio_group *blkg, + struct blkio_group *curr_blkg) {} +static inline void blkio_end_empty_time(struct blkio_group_stats *stats) {} +#endif + +void blkiocg_update_io_add_stats(struct blkio_group *blkg, + struct blkio_group *curr_blkg, bool direction, + bool sync) +{ + unsigned long flags; + + spin_lock_irqsave(&blkg->stats_lock, flags); + blkio_add_stat(blkg->stats.stat_arr[BLKIO_STAT_QUEUED], 1, direction, + sync); + blkio_end_empty_time(&blkg->stats); + blkio_set_start_group_wait_time(blkg, curr_blkg); + spin_unlock_irqrestore(&blkg->stats_lock, flags); +} +EXPORT_SYMBOL_GPL(blkiocg_update_io_add_stats); + +void blkiocg_update_io_remove_stats(struct blkio_group *blkg, + bool direction, bool sync) +{ + unsigned long flags; + + spin_lock_irqsave(&blkg->stats_lock, flags); + blkio_check_and_dec_stat(blkg->stats.stat_arr[BLKIO_STAT_QUEUED], + direction, sync); + spin_unlock_irqrestore(&blkg->stats_lock, flags); +} +EXPORT_SYMBOL_GPL(blkiocg_update_io_remove_stats); + +void blkiocg_update_timeslice_used(struct blkio_group *blkg, unsigned long time) +{ + unsigned long flags; + + spin_lock_irqsave(&blkg->stats_lock, flags); + blkg->stats.time += time; + spin_unlock_irqrestore(&blkg->stats_lock, flags); +} +EXPORT_SYMBOL_GPL(blkiocg_update_timeslice_used); + +void blkiocg_set_start_empty_time(struct blkio_group *blkg, bool ignore) +{ + unsigned long flags; + struct blkio_group_stats *stats; + + spin_lock_irqsave(&blkg->stats_lock, flags); + stats = &blkg->stats; + + if (stats->stat_arr[BLKIO_STAT_QUEUED][BLKIO_STAT_READ] || + stats->stat_arr[BLKIO_STAT_QUEUED][BLKIO_STAT_WRITE]) { + spin_unlock_irqrestore(&blkg->stats_lock, flags); + return; + } + + /* + * If ignore is set, we do not panic on the empty flag being set + * already. This is to avoid cases where there are superfluous timeslice + * complete events (for eg., forced_dispatch in CFQ) when no IOs are + * served which could result in triggering the empty check incorrectly. + */ + BUG_ON(!ignore && blkio_blkg_empty(stats)); + stats->start_empty_time = sched_clock(); + blkio_mark_blkg_empty(stats); + spin_unlock_irqrestore(&blkg->stats_lock, flags); +} +EXPORT_SYMBOL_GPL(blkiocg_set_start_empty_time); + +void blkiocg_update_dispatch_stats(struct blkio_group *blkg, + uint64_t bytes, bool direction, bool sync) +{ + struct blkio_group_stats *stats; + unsigned long flags; + + spin_lock_irqsave(&blkg->stats_lock, flags); + stats = &blkg->stats; + stats->sectors += bytes >> 9; + blkio_add_stat(stats->stat_arr[BLKIO_STAT_SERVICED], 1, direction, + sync); + blkio_add_stat(stats->stat_arr[BLKIO_STAT_SERVICE_BYTES], bytes, + direction, sync); + spin_unlock_irqrestore(&blkg->stats_lock, flags); +} +EXPORT_SYMBOL_GPL(blkiocg_update_dispatch_stats); + +void blkiocg_update_completion_stats(struct blkio_group *blkg, + uint64_t start_time, uint64_t io_start_time, bool direction, bool sync) +{ + struct blkio_group_stats *stats; + unsigned long flags; + unsigned long long now = sched_clock(); + + spin_lock_irqsave(&blkg->stats_lock, flags); + stats = &blkg->stats; + if (time_after64(now, io_start_time)) + blkio_add_stat(stats->stat_arr[BLKIO_STAT_SERVICE_TIME], + now - io_start_time, direction, sync); + if (time_after64(io_start_time, start_time)) + blkio_add_stat(stats->stat_arr[BLKIO_STAT_WAIT_TIME], + io_start_time - start_time, direction, sync); + spin_unlock_irqrestore(&blkg->stats_lock, flags); +} +EXPORT_SYMBOL_GPL(blkiocg_update_completion_stats); + +void blkiocg_update_io_merged_stats(struct blkio_group *blkg, bool direction, + bool sync) +{ + unsigned long flags; + + spin_lock_irqsave(&blkg->stats_lock, flags); + blkio_add_stat(blkg->stats.stat_arr[BLKIO_STAT_MERGED], 1, direction, + sync); + spin_unlock_irqrestore(&blkg->stats_lock, flags); +} +EXPORT_SYMBOL_GPL(blkiocg_update_io_merged_stats); void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg, struct blkio_group *blkg, void *key, dev_t dev) @@ -154,6 +433,7 @@ blkiocg_weight_write(struct cgroup *cgroup, struct cftype *cftype, u64 val) struct blkio_group *blkg; struct hlist_node *n; struct blkio_policy_type *blkiop; + struct blkio_policy_node *pn; if (val < BLKIO_WEIGHT_MIN || val > BLKIO_WEIGHT_MAX) return -EINVAL; @@ -162,7 +442,13 @@ blkiocg_weight_write(struct cgroup *cgroup, struct cftype *cftype, u64 val) spin_lock(&blkio_list_lock); spin_lock_irq(&blkcg->lock); blkcg->weight = (unsigned int)val; + hlist_for_each_entry(blkg, n, &blkcg->blkg_list, blkcg_node) { + pn = blkio_policy_search_node(blkcg, blkg->dev); + + if (pn) + continue; + list_for_each_entry(blkiop, &blkio_list, list) blkiop->ops.blkio_update_group_weight_fn(blkg, blkcg->weight); @@ -172,13 +458,154 @@ blkiocg_weight_write(struct cgroup *cgroup, struct cftype *cftype, u64 val) return 0; } -#define SHOW_FUNCTION_PER_GROUP(__VAR) \ +static int +blkiocg_reset_stats(struct cgroup *cgroup, struct cftype *cftype, u64 val) +{ + struct blkio_cgroup *blkcg; + struct blkio_group *blkg; + struct blkio_group_stats *stats; + struct hlist_node *n; + uint64_t queued[BLKIO_STAT_TOTAL]; + int i; +#ifdef CONFIG_DEBUG_BLK_CGROUP + bool idling, waiting, empty; + unsigned long long now = sched_clock(); +#endif + + blkcg = cgroup_to_blkio_cgroup(cgroup); + spin_lock_irq(&blkcg->lock); + hlist_for_each_entry(blkg, n, &blkcg->blkg_list, blkcg_node) { + spin_lock(&blkg->stats_lock); + stats = &blkg->stats; +#ifdef CONFIG_DEBUG_BLK_CGROUP + idling = blkio_blkg_idling(stats); + waiting = blkio_blkg_waiting(stats); + empty = blkio_blkg_empty(stats); +#endif + for (i = 0; i < BLKIO_STAT_TOTAL; i++) + queued[i] = stats->stat_arr[BLKIO_STAT_QUEUED][i]; + memset(stats, 0, sizeof(struct blkio_group_stats)); + for (i = 0; i < BLKIO_STAT_TOTAL; i++) + stats->stat_arr[BLKIO_STAT_QUEUED][i] = queued[i]; +#ifdef CONFIG_DEBUG_BLK_CGROUP + if (idling) { + blkio_mark_blkg_idling(stats); + stats->start_idle_time = now; + } + if (waiting) { + blkio_mark_blkg_waiting(stats); + stats->start_group_wait_time = now; + } + if (empty) { + blkio_mark_blkg_empty(stats); + stats->start_empty_time = now; + } +#endif + spin_unlock(&blkg->stats_lock); + } + spin_unlock_irq(&blkcg->lock); + return 0; +} + +static void blkio_get_key_name(enum stat_sub_type type, dev_t dev, char *str, + int chars_left, bool diskname_only) +{ + snprintf(str, chars_left, "%d:%d", MAJOR(dev), MINOR(dev)); + chars_left -= strlen(str); + if (chars_left <= 0) { + printk(KERN_WARNING + "Possibly incorrect cgroup stat display format"); + return; + } + if (diskname_only) + return; + switch (type) { + case BLKIO_STAT_READ: + strlcat(str, " Read", chars_left); + break; + case BLKIO_STAT_WRITE: + strlcat(str, " Write", chars_left); + break; + case BLKIO_STAT_SYNC: + strlcat(str, " Sync", chars_left); + break; + case BLKIO_STAT_ASYNC: + strlcat(str, " Async", chars_left); + break; + case BLKIO_STAT_TOTAL: + strlcat(str, " Total", chars_left); + break; + default: + strlcat(str, " Invalid", chars_left); + } +} + +static uint64_t blkio_fill_stat(char *str, int chars_left, uint64_t val, + struct cgroup_map_cb *cb, dev_t dev) +{ + blkio_get_key_name(0, dev, str, chars_left, true); + cb->fill(cb, str, val); + return val; +} + +/* This should be called with blkg->stats_lock held */ +static uint64_t blkio_get_stat(struct blkio_group *blkg, + struct cgroup_map_cb *cb, dev_t dev, enum stat_type type) +{ + uint64_t disk_total; + char key_str[MAX_KEY_LEN]; + enum stat_sub_type sub_type; + + if (type == BLKIO_STAT_TIME) + return blkio_fill_stat(key_str, MAX_KEY_LEN - 1, + blkg->stats.time, cb, dev); + if (type == BLKIO_STAT_SECTORS) + return blkio_fill_stat(key_str, MAX_KEY_LEN - 1, + blkg->stats.sectors, cb, dev); +#ifdef CONFIG_DEBUG_BLK_CGROUP + if (type == BLKIO_STAT_AVG_QUEUE_SIZE) { + uint64_t sum = blkg->stats.avg_queue_size_sum; + uint64_t samples = blkg->stats.avg_queue_size_samples; + if (samples) + do_div(sum, samples); + else + sum = 0; + return blkio_fill_stat(key_str, MAX_KEY_LEN - 1, sum, cb, dev); + } + if (type == BLKIO_STAT_GROUP_WAIT_TIME) + return blkio_fill_stat(key_str, MAX_KEY_LEN - 1, + blkg->stats.group_wait_time, cb, dev); + if (type == BLKIO_STAT_IDLE_TIME) + return blkio_fill_stat(key_str, MAX_KEY_LEN - 1, + blkg->stats.idle_time, cb, dev); + if (type == BLKIO_STAT_EMPTY_TIME) + return blkio_fill_stat(key_str, MAX_KEY_LEN - 1, + blkg->stats.empty_time, cb, dev); + if (type == BLKIO_STAT_DEQUEUE) + return blkio_fill_stat(key_str, MAX_KEY_LEN - 1, + blkg->stats.dequeue, cb, dev); +#endif + + for (sub_type = BLKIO_STAT_READ; sub_type < BLKIO_STAT_TOTAL; + sub_type++) { + blkio_get_key_name(sub_type, dev, key_str, MAX_KEY_LEN, false); + cb->fill(cb, key_str, blkg->stats.stat_arr[type][sub_type]); + } + disk_total = blkg->stats.stat_arr[type][BLKIO_STAT_READ] + + blkg->stats.stat_arr[type][BLKIO_STAT_WRITE]; + blkio_get_key_name(BLKIO_STAT_TOTAL, dev, key_str, MAX_KEY_LEN, false); + cb->fill(cb, key_str, disk_total); + return disk_total; +} + +#define SHOW_FUNCTION_PER_GROUP(__VAR, type, show_total) \ static int blkiocg_##__VAR##_read(struct cgroup *cgroup, \ - struct cftype *cftype, struct seq_file *m) \ + struct cftype *cftype, struct cgroup_map_cb *cb) \ { \ struct blkio_cgroup *blkcg; \ struct blkio_group *blkg; \ struct hlist_node *n; \ + uint64_t cgroup_total = 0; \ \ if (!cgroup_lock_live_group(cgroup)) \ return -ENODEV; \ @@ -186,50 +613,295 @@ static int blkiocg_##__VAR##_read(struct cgroup *cgroup, \ blkcg = cgroup_to_blkio_cgroup(cgroup); \ rcu_read_lock(); \ hlist_for_each_entry_rcu(blkg, n, &blkcg->blkg_list, blkcg_node) {\ - if (blkg->dev) \ - seq_printf(m, "%u:%u %lu\n", MAJOR(blkg->dev), \ - MINOR(blkg->dev), blkg->__VAR); \ + if (blkg->dev) { \ + spin_lock_irq(&blkg->stats_lock); \ + cgroup_total += blkio_get_stat(blkg, cb, \ + blkg->dev, type); \ + spin_unlock_irq(&blkg->stats_lock); \ + } \ } \ + if (show_total) \ + cb->fill(cb, "Total", cgroup_total); \ rcu_read_unlock(); \ cgroup_unlock(); \ return 0; \ } -SHOW_FUNCTION_PER_GROUP(time); -SHOW_FUNCTION_PER_GROUP(sectors); +SHOW_FUNCTION_PER_GROUP(time, BLKIO_STAT_TIME, 0); +SHOW_FUNCTION_PER_GROUP(sectors, BLKIO_STAT_SECTORS, 0); +SHOW_FUNCTION_PER_GROUP(io_service_bytes, BLKIO_STAT_SERVICE_BYTES, 1); +SHOW_FUNCTION_PER_GROUP(io_serviced, BLKIO_STAT_SERVICED, 1); +SHOW_FUNCTION_PER_GROUP(io_service_time, BLKIO_STAT_SERVICE_TIME, 1); +SHOW_FUNCTION_PER_GROUP(io_wait_time, BLKIO_STAT_WAIT_TIME, 1); +SHOW_FUNCTION_PER_GROUP(io_merged, BLKIO_STAT_MERGED, 1); +SHOW_FUNCTION_PER_GROUP(io_queued, BLKIO_STAT_QUEUED, 1); #ifdef CONFIG_DEBUG_BLK_CGROUP -SHOW_FUNCTION_PER_GROUP(dequeue); +SHOW_FUNCTION_PER_GROUP(dequeue, BLKIO_STAT_DEQUEUE, 0); +SHOW_FUNCTION_PER_GROUP(avg_queue_size, BLKIO_STAT_AVG_QUEUE_SIZE, 0); +SHOW_FUNCTION_PER_GROUP(group_wait_time, BLKIO_STAT_GROUP_WAIT_TIME, 0); +SHOW_FUNCTION_PER_GROUP(idle_time, BLKIO_STAT_IDLE_TIME, 0); +SHOW_FUNCTION_PER_GROUP(empty_time, BLKIO_STAT_EMPTY_TIME, 0); #endif #undef SHOW_FUNCTION_PER_GROUP -#ifdef CONFIG_DEBUG_BLK_CGROUP -void blkiocg_update_blkio_group_dequeue_stats(struct blkio_group *blkg, - unsigned long dequeue) +static int blkio_check_dev_num(dev_t dev) { - blkg->dequeue += dequeue; + int part = 0; + struct gendisk *disk; + + disk = get_gendisk(dev, &part); + if (!disk || part) + return -ENODEV; + + return 0; +} + +static int blkio_policy_parse_and_set(char *buf, + struct blkio_policy_node *newpn) +{ + char *s[4], *p, *major_s = NULL, *minor_s = NULL; + int ret; + unsigned long major, minor, temp; + int i = 0; + dev_t dev; + + memset(s, 0, sizeof(s)); + + while ((p = strsep(&buf, " ")) != NULL) { + if (!*p) + continue; + + s[i++] = p; + + /* Prevent from inputing too many things */ + if (i == 3) + break; + } + + if (i != 2) + return -EINVAL; + + p = strsep(&s[0], ":"); + if (p != NULL) + major_s = p; + else + return -EINVAL; + + minor_s = s[0]; + if (!minor_s) + return -EINVAL; + + ret = strict_strtoul(major_s, 10, &major); + if (ret) + return -EINVAL; + + ret = strict_strtoul(minor_s, 10, &minor); + if (ret) + return -EINVAL; + + dev = MKDEV(major, minor); + + ret = blkio_check_dev_num(dev); + if (ret) + return ret; + + newpn->dev = dev; + + if (s[1] == NULL) + return -EINVAL; + + ret = strict_strtoul(s[1], 10, &temp); + if (ret || (temp < BLKIO_WEIGHT_MIN && temp > 0) || + temp > BLKIO_WEIGHT_MAX) + return -EINVAL; + + newpn->weight = temp; + + return 0; +} + +unsigned int blkcg_get_weight(struct blkio_cgroup *blkcg, + dev_t dev) +{ + struct blkio_policy_node *pn; + + pn = blkio_policy_search_node(blkcg, dev); + if (pn) + return pn->weight; + else + return blkcg->weight; +} +EXPORT_SYMBOL_GPL(blkcg_get_weight); + + +static int blkiocg_weight_device_write(struct cgroup *cgrp, struct cftype *cft, + const char *buffer) +{ + int ret = 0; + char *buf; + struct blkio_policy_node *newpn, *pn; + struct blkio_cgroup *blkcg; + struct blkio_group *blkg; + int keep_newpn = 0; + struct hlist_node *n; + struct blkio_policy_type *blkiop; + + buf = kstrdup(buffer, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + newpn = kzalloc(sizeof(*newpn), GFP_KERNEL); + if (!newpn) { + ret = -ENOMEM; + goto free_buf; + } + + ret = blkio_policy_parse_and_set(buf, newpn); + if (ret) + goto free_newpn; + + blkcg = cgroup_to_blkio_cgroup(cgrp); + + spin_lock_irq(&blkcg->lock); + + pn = blkio_policy_search_node(blkcg, newpn->dev); + if (!pn) { + if (newpn->weight != 0) { + blkio_policy_insert_node(blkcg, newpn); + keep_newpn = 1; + } + spin_unlock_irq(&blkcg->lock); + goto update_io_group; + } + + if (newpn->weight == 0) { + /* weight == 0 means deleteing a specific weight */ + blkio_policy_delete_node(pn); + spin_unlock_irq(&blkcg->lock); + goto update_io_group; + } + spin_unlock_irq(&blkcg->lock); + + pn->weight = newpn->weight; + +update_io_group: + /* update weight for each cfqg */ + spin_lock(&blkio_list_lock); + spin_lock_irq(&blkcg->lock); + + hlist_for_each_entry(blkg, n, &blkcg->blkg_list, blkcg_node) { + if (newpn->dev == blkg->dev) { + list_for_each_entry(blkiop, &blkio_list, list) + blkiop->ops.blkio_update_group_weight_fn(blkg, + newpn->weight ? + newpn->weight : + blkcg->weight); + } + } + + spin_unlock_irq(&blkcg->lock); + spin_unlock(&blkio_list_lock); + +free_newpn: + if (!keep_newpn) + kfree(newpn); +free_buf: + kfree(buf); + return ret; +} + +static int blkiocg_weight_device_read(struct cgroup *cgrp, struct cftype *cft, + struct seq_file *m) +{ + struct blkio_cgroup *blkcg; + struct blkio_policy_node *pn; + + seq_printf(m, "dev\tweight\n"); + + blkcg = cgroup_to_blkio_cgroup(cgrp); + if (list_empty(&blkcg->policy_list)) + goto out; + + spin_lock_irq(&blkcg->lock); + list_for_each_entry(pn, &blkcg->policy_list, node) { + seq_printf(m, "%u:%u\t%u\n", MAJOR(pn->dev), + MINOR(pn->dev), pn->weight); + } + spin_unlock_irq(&blkcg->lock); + +out: + return 0; } -EXPORT_SYMBOL_GPL(blkiocg_update_blkio_group_dequeue_stats); -#endif struct cftype blkio_files[] = { { + .name = "weight_device", + .read_seq_string = blkiocg_weight_device_read, + .write_string = blkiocg_weight_device_write, + .max_write_len = 256, + }, + { .name = "weight", .read_u64 = blkiocg_weight_read, .write_u64 = blkiocg_weight_write, }, { .name = "time", - .read_seq_string = blkiocg_time_read, + .read_map = blkiocg_time_read, }, { .name = "sectors", - .read_seq_string = blkiocg_sectors_read, + .read_map = blkiocg_sectors_read, + }, + { + .name = "io_service_bytes", + .read_map = blkiocg_io_service_bytes_read, + }, + { + .name = "io_serviced", + .read_map = blkiocg_io_serviced_read, + }, + { + .name = "io_service_time", + .read_map = blkiocg_io_service_time_read, + }, + { + .name = "io_wait_time", + .read_map = blkiocg_io_wait_time_read, + }, + { + .name = "io_merged", + .read_map = blkiocg_io_merged_read, + }, + { + .name = "io_queued", + .read_map = blkiocg_io_queued_read, + }, + { + .name = "reset_stats", + .write_u64 = blkiocg_reset_stats, }, #ifdef CONFIG_DEBUG_BLK_CGROUP - { + { + .name = "avg_queue_size", + .read_map = blkiocg_avg_queue_size_read, + }, + { + .name = "group_wait_time", + .read_map = blkiocg_group_wait_time_read, + }, + { + .name = "idle_time", + .read_map = blkiocg_idle_time_read, + }, + { + .name = "empty_time", + .read_map = blkiocg_empty_time_read, + }, + { .name = "dequeue", - .read_seq_string = blkiocg_dequeue_read, - }, + .read_map = blkiocg_dequeue_read, + }, #endif }; @@ -246,6 +918,7 @@ static void blkiocg_destroy(struct cgroup_subsys *subsys, struct cgroup *cgroup) struct blkio_group *blkg; void *key; struct blkio_policy_type *blkiop; + struct blkio_policy_node *pn, *pntmp; rcu_read_lock(); remove_entry: @@ -276,7 +949,12 @@ remove_entry: blkiop->ops.blkio_unlink_group_fn(key, blkg); spin_unlock(&blkio_list_lock); goto remove_entry; + done: + list_for_each_entry_safe(pn, pntmp, &blkcg->policy_list, node) { + blkio_policy_delete_node(pn); + kfree(pn); + } free_css_id(&blkio_subsys, &blkcg->css); rcu_read_unlock(); if (blkcg != &blkio_root_cgroup) @@ -307,6 +985,7 @@ done: spin_lock_init(&blkcg->lock); INIT_HLIST_HEAD(&blkcg->blkg_list); + INIT_LIST_HEAD(&blkcg->policy_list); return &blkcg->css; } diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h index 8ccc204..1d409ad 100644 --- a/block/blk-cgroup.h +++ b/block/blk-cgroup.h @@ -23,11 +23,84 @@ extern struct cgroup_subsys blkio_subsys; #define blkio_subsys_id blkio_subsys.subsys_id #endif +enum stat_type { + /* Total time spent (in ns) between request dispatch to the driver and + * request completion for IOs doen by this cgroup. This may not be + * accurate when NCQ is turned on. */ + BLKIO_STAT_SERVICE_TIME = 0, + /* Total bytes transferred */ + BLKIO_STAT_SERVICE_BYTES, + /* Total IOs serviced, post merge */ + BLKIO_STAT_SERVICED, + /* Total time spent waiting in scheduler queue in ns */ + BLKIO_STAT_WAIT_TIME, + /* Number of IOs merged */ + BLKIO_STAT_MERGED, + /* Number of IOs queued up */ + BLKIO_STAT_QUEUED, + /* All the single valued stats go below this */ + BLKIO_STAT_TIME, + BLKIO_STAT_SECTORS, +#ifdef CONFIG_DEBUG_BLK_CGROUP + BLKIO_STAT_AVG_QUEUE_SIZE, + BLKIO_STAT_IDLE_TIME, + BLKIO_STAT_EMPTY_TIME, + BLKIO_STAT_GROUP_WAIT_TIME, + BLKIO_STAT_DEQUEUE +#endif +}; + +enum stat_sub_type { + BLKIO_STAT_READ = 0, + BLKIO_STAT_WRITE, + BLKIO_STAT_SYNC, + BLKIO_STAT_ASYNC, + BLKIO_STAT_TOTAL +}; + +/* blkg state flags */ +enum blkg_state_flags { + BLKG_waiting = 0, + BLKG_idling, + BLKG_empty, +}; + struct blkio_cgroup { struct cgroup_subsys_state css; unsigned int weight; spinlock_t lock; struct hlist_head blkg_list; + struct list_head policy_list; /* list of blkio_policy_node */ +}; + +struct blkio_group_stats { + /* total disk time and nr sectors dispatched by this group */ + uint64_t time; + uint64_t sectors; + uint64_t stat_arr[BLKIO_STAT_QUEUED + 1][BLKIO_STAT_TOTAL]; +#ifdef CONFIG_DEBUG_BLK_CGROUP + /* Sum of number of IOs queued across all samples */ + uint64_t avg_queue_size_sum; + /* Count of samples taken for average */ + uint64_t avg_queue_size_samples; + /* How many times this group has been removed from service tree */ + unsigned long dequeue; + + /* Total time spent waiting for it to be assigned a timeslice. */ + uint64_t group_wait_time; + uint64_t start_group_wait_time; + + /* Time spent idling for this blkio_group */ + uint64_t idle_time; + uint64_t start_idle_time; + /* + * Total time when we have requests queued and do not contain the + * current active queue. + */ + uint64_t empty_time; + uint64_t start_empty_time; + uint16_t flags; +#endif }; struct blkio_group { @@ -38,17 +111,24 @@ struct blkio_group { #ifdef CONFIG_DEBUG_BLK_CGROUP /* Store cgroup path */ char path[128]; - /* How many times this group has been removed from service tree */ - unsigned long dequeue; #endif /* The device MKDEV(major, minor), this group has been created for */ - dev_t dev; + dev_t dev; - /* total disk time and nr sectors dispatched by this group */ - unsigned long time; - unsigned long sectors; + /* Need to serialize the stats in the case of reset/update */ + spinlock_t stats_lock; + struct blkio_group_stats stats; +}; + +struct blkio_policy_node { + struct list_head node; + dev_t dev; + unsigned int weight; }; +extern unsigned int blkcg_get_weight(struct blkio_cgroup *blkcg, + dev_t dev); + typedef void (blkio_unlink_group_fn) (void *key, struct blkio_group *blkg); typedef void (blkio_update_group_weight_fn) (struct blkio_group *blkg, unsigned int weight); @@ -89,12 +169,44 @@ static inline char *blkg_path(struct blkio_group *blkg) { return blkg->path; } -void blkiocg_update_blkio_group_dequeue_stats(struct blkio_group *blkg, +void blkiocg_update_avg_queue_size_stats(struct blkio_group *blkg); +void blkiocg_update_dequeue_stats(struct blkio_group *blkg, unsigned long dequeue); +void blkiocg_update_set_idle_time_stats(struct blkio_group *blkg); +void blkiocg_update_idle_time_stats(struct blkio_group *blkg); +void blkiocg_set_start_empty_time(struct blkio_group *blkg, bool ignore); + +#define BLKG_FLAG_FNS(name) \ +static inline void blkio_mark_blkg_##name( \ + struct blkio_group_stats *stats) \ +{ \ + stats->flags |= (1 << BLKG_##name); \ +} \ +static inline void blkio_clear_blkg_##name( \ + struct blkio_group_stats *stats) \ +{ \ + stats->flags &= ~(1 << BLKG_##name); \ +} \ +static inline int blkio_blkg_##name(struct blkio_group_stats *stats) \ +{ \ + return (stats->flags & (1 << BLKG_##name)) != 0; \ +} \ + +BLKG_FLAG_FNS(waiting) +BLKG_FLAG_FNS(idling) +BLKG_FLAG_FNS(empty) +#undef BLKG_FLAG_FNS #else static inline char *blkg_path(struct blkio_group *blkg) { return NULL; } -static inline void blkiocg_update_blkio_group_dequeue_stats( - struct blkio_group *blkg, unsigned long dequeue) {} +static inline void blkiocg_update_avg_queue_size_stats( + struct blkio_group *blkg) {} +static inline void blkiocg_update_dequeue_stats(struct blkio_group *blkg, + unsigned long dequeue) {} +static inline void blkiocg_update_set_idle_time_stats(struct blkio_group *blkg) +{} +static inline void blkiocg_update_idle_time_stats(struct blkio_group *blkg) {} +static inline void blkiocg_set_start_empty_time(struct blkio_group *blkg, + bool ignore) {} #endif #if defined(CONFIG_BLK_CGROUP) || defined(CONFIG_BLK_CGROUP_MODULE) @@ -105,26 +217,45 @@ extern void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg, extern int blkiocg_del_blkio_group(struct blkio_group *blkg); extern struct blkio_group *blkiocg_lookup_group(struct blkio_cgroup *blkcg, void *key); -void blkiocg_update_blkio_group_stats(struct blkio_group *blkg, - unsigned long time, unsigned long sectors); +void blkio_group_init(struct blkio_group *blkg); +void blkiocg_update_timeslice_used(struct blkio_group *blkg, + unsigned long time); +void blkiocg_update_dispatch_stats(struct blkio_group *blkg, uint64_t bytes, + bool direction, bool sync); +void blkiocg_update_completion_stats(struct blkio_group *blkg, + uint64_t start_time, uint64_t io_start_time, bool direction, bool sync); +void blkiocg_update_io_merged_stats(struct blkio_group *blkg, bool direction, + bool sync); +void blkiocg_update_io_add_stats(struct blkio_group *blkg, + struct blkio_group *curr_blkg, bool direction, bool sync); +void blkiocg_update_io_remove_stats(struct blkio_group *blkg, + bool direction, bool sync); #else struct cgroup; static inline struct blkio_cgroup * cgroup_to_blkio_cgroup(struct cgroup *cgroup) { return NULL; } +static inline void blkio_group_init(struct blkio_group *blkg) {} static inline void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg, - struct blkio_group *blkg, void *key, dev_t dev) -{ -} + struct blkio_group *blkg, void *key, dev_t dev) {} static inline int blkiocg_del_blkio_group(struct blkio_group *blkg) { return 0; } static inline struct blkio_group * blkiocg_lookup_group(struct blkio_cgroup *blkcg, void *key) { return NULL; } -static inline void blkiocg_update_blkio_group_stats(struct blkio_group *blkg, - unsigned long time, unsigned long sectors) -{ -} +static inline void blkiocg_update_timeslice_used(struct blkio_group *blkg, + unsigned long time) {} +static inline void blkiocg_update_dispatch_stats(struct blkio_group *blkg, + uint64_t bytes, bool direction, bool sync) {} +static inline void blkiocg_update_completion_stats(struct blkio_group *blkg, + uint64_t start_time, uint64_t io_start_time, bool direction, + bool sync) {} +static inline void blkiocg_update_io_merged_stats(struct blkio_group *blkg, + bool direction, bool sync) {} +static inline void blkiocg_update_io_add_stats(struct blkio_group *blkg, + struct blkio_group *curr_blkg, bool direction, bool sync) {} +static inline void blkiocg_update_io_remove_stats(struct blkio_group *blkg, + bool direction, bool sync) {} #endif #endif /* _BLK_CGROUP_H */ diff --git a/block/blk-core.c b/block/blk-core.c index 9fe174d..e9a5ae2 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -127,6 +127,7 @@ void blk_rq_init(struct request_queue *q, struct request *rq) rq->tag = -1; rq->ref_count = 1; rq->start_time = jiffies; + set_start_time_ns(rq); } EXPORT_SYMBOL(blk_rq_init); @@ -450,6 +451,7 @@ void blk_cleanup_queue(struct request_queue *q) */ blk_sync_queue(q); + del_timer_sync(&q->backing_dev_info.laptop_mode_wb_timer); mutex_lock(&q->sysfs_lock); queue_flag_set_unlocked(QUEUE_FLAG_DEAD, q); mutex_unlock(&q->sysfs_lock); @@ -510,6 +512,8 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) return NULL; } + setup_timer(&q->backing_dev_info.laptop_mode_wb_timer, + laptop_mode_timer_fn, (unsigned long) q); init_timer(&q->unplug_timer); setup_timer(&q->timeout, blk_rq_timed_out_timer, (unsigned long) q); INIT_LIST_HEAD(&q->timeout_list); @@ -1198,6 +1202,7 @@ static int __make_request(struct request_queue *q, struct bio *bio) if (!blk_rq_cpu_valid(req)) req->cpu = bio->bi_comp_cpu; drive_stat_acct(req, 0); + elv_bio_merged(q, req, bio); if (!attempt_back_merge(q, req)) elv_merged_request(q, req, el_ret); goto out; @@ -1231,6 +1236,7 @@ static int __make_request(struct request_queue *q, struct bio *bio) if (!blk_rq_cpu_valid(req)) req->cpu = bio->bi_comp_cpu; drive_stat_acct(req, 0); + elv_bio_merged(q, req, bio); if (!attempt_front_merge(q, req)) elv_merged_request(q, req, el_ret); goto out; @@ -1855,8 +1861,10 @@ void blk_dequeue_request(struct request *rq) * and to it is freed is accounted as io that is in progress at * the driver side. */ - if (blk_account_rq(rq)) + if (blk_account_rq(rq)) { q->in_flight[rq_is_sync(rq)]++; + set_io_start_time_ns(rq); + } } /** @@ -2098,7 +2106,7 @@ static void blk_finish_request(struct request *req, int error) BUG_ON(blk_queued_rq(req)); if (unlikely(laptop_mode) && blk_fs_request(req)) - laptop_io_completion(); + laptop_io_completion(&req->q->backing_dev_info); blk_delete_timer(req); @@ -2517,4 +2525,3 @@ int __init blk_dev_init(void) return 0; } - diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index 838834b..9e0df2b 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -143,8 +143,6 @@ struct cfq_queue { struct cfq_queue *new_cfqq; struct cfq_group *cfqg; struct cfq_group *orig_cfqg; - /* Sectors dispatched in current dispatch round */ - unsigned long nr_sectors; }; /* @@ -858,7 +856,7 @@ cfq_group_service_tree_del(struct cfq_data *cfqd, struct cfq_group *cfqg) if (!RB_EMPTY_NODE(&cfqg->rb_node)) cfq_rb_erase(&cfqg->rb_node, st); cfqg->saved_workload_slice = 0; - blkiocg_update_blkio_group_dequeue_stats(&cfqg->blkg, 1); + blkiocg_update_dequeue_stats(&cfqg->blkg, 1); } static inline unsigned int cfq_cfqq_slice_usage(struct cfq_queue *cfqq) @@ -884,13 +882,12 @@ static inline unsigned int cfq_cfqq_slice_usage(struct cfq_queue *cfqq) slice_used = cfqq->allocated_slice; } - cfq_log_cfqq(cfqq->cfqd, cfqq, "sl_used=%u sect=%lu", slice_used, - cfqq->nr_sectors); + cfq_log_cfqq(cfqq->cfqd, cfqq, "sl_used=%u", slice_used); return slice_used; } static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg, - struct cfq_queue *cfqq) + struct cfq_queue *cfqq, bool forced) { struct cfq_rb_root *st = &cfqd->grp_service_tree; unsigned int used_sl, charge_sl; @@ -919,8 +916,8 @@ 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); - blkiocg_update_blkio_group_stats(&cfqg->blkg, used_sl, - cfqq->nr_sectors); + blkiocg_update_timeslice_used(&cfqg->blkg, used_sl); + blkiocg_set_start_empty_time(&cfqg->blkg, forced); } #ifdef CONFIG_CFQ_GROUP_IOSCHED @@ -961,10 +958,10 @@ cfq_find_alloc_cfqg(struct cfq_data *cfqd, struct cgroup *cgroup, int create) if (!cfqg) goto done; - cfqg->weight = blkcg->weight; for_each_cfqg_st(cfqg, i, j, st) *st = CFQ_RB_ROOT; RB_CLEAR_NODE(&cfqg->rb_node); + blkio_group_init(&cfqg->blkg); /* * Take the initial reference that will be released on destroy @@ -978,6 +975,7 @@ cfq_find_alloc_cfqg(struct cfq_data *cfqd, struct cgroup *cgroup, int create) sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor); blkiocg_add_blkio_group(blkcg, &cfqg->blkg, (void *)cfqd, MKDEV(major, minor)); + cfqg->weight = blkcg_get_weight(blkcg, cfqg->blkg.dev); /* Add group on cfqd list */ hlist_add_head(&cfqg->cfqd_node, &cfqd->cfqg_list); @@ -1389,7 +1387,12 @@ static void cfq_reposition_rq_rb(struct cfq_queue *cfqq, struct request *rq) { elv_rb_del(&cfqq->sort_list, rq); cfqq->queued[rq_is_sync(rq)]--; + blkiocg_update_io_remove_stats(&cfqq->cfqg->blkg, rq_data_dir(rq), + rq_is_sync(rq)); cfq_add_rq_rb(rq); + blkiocg_update_io_add_stats( + &cfqq->cfqg->blkg, &cfqq->cfqd->serving_group->blkg, + rq_data_dir(rq), rq_is_sync(rq)); } static struct request * @@ -1445,6 +1448,8 @@ static void cfq_remove_request(struct request *rq) cfq_del_rq_rb(rq); cfqq->cfqd->rq_queued--; + blkiocg_update_io_remove_stats(&cfqq->cfqg->blkg, rq_data_dir(rq), + rq_is_sync(rq)); if (rq_is_meta(rq)) { WARN_ON(!cfqq->meta_pending); cfqq->meta_pending--; @@ -1476,6 +1481,14 @@ static void cfq_merged_request(struct request_queue *q, struct request *req, } } +static void cfq_bio_merged(struct request_queue *q, struct request *req, + struct bio *bio) +{ + struct cfq_queue *cfqq = RQ_CFQQ(req); + blkiocg_update_io_merged_stats(&cfqq->cfqg->blkg, bio_data_dir(bio), + cfq_bio_sync(bio)); +} + static void cfq_merged_requests(struct request_queue *q, struct request *rq, struct request *next) @@ -1493,6 +1506,8 @@ cfq_merged_requests(struct request_queue *q, struct request *rq, if (cfqq->next_rq == next) cfqq->next_rq = rq; cfq_remove_request(next); + blkiocg_update_io_merged_stats(&cfqq->cfqg->blkg, rq_data_dir(next), + rq_is_sync(next)); } static int cfq_allow_merge(struct request_queue *q, struct request *rq, @@ -1520,18 +1535,24 @@ static int cfq_allow_merge(struct request_queue *q, struct request *rq, return cfqq == RQ_CFQQ(rq); } +static inline void cfq_del_timer(struct cfq_data *cfqd, struct cfq_queue *cfqq) +{ + del_timer(&cfqd->idle_slice_timer); + blkiocg_update_idle_time_stats(&cfqq->cfqg->blkg); +} + static void __cfq_set_active_queue(struct cfq_data *cfqd, struct cfq_queue *cfqq) { if (cfqq) { cfq_log_cfqq(cfqd, cfqq, "set_active wl_prio:%d wl_type:%d", cfqd->serving_prio, cfqd->serving_type); + blkiocg_update_avg_queue_size_stats(&cfqq->cfqg->blkg); cfqq->slice_start = 0; cfqq->dispatch_start = jiffies; cfqq->allocated_slice = 0; cfqq->slice_end = 0; cfqq->slice_dispatch = 0; - cfqq->nr_sectors = 0; cfq_clear_cfqq_wait_request(cfqq); cfq_clear_cfqq_must_dispatch(cfqq); @@ -1539,7 +1560,7 @@ static void __cfq_set_active_queue(struct cfq_data *cfqd, cfq_clear_cfqq_fifo_expire(cfqq); cfq_mark_cfqq_slice_new(cfqq); - del_timer(&cfqd->idle_slice_timer); + cfq_del_timer(cfqd, cfqq); } cfqd->active_queue = cfqq; @@ -1550,12 +1571,12 @@ static void __cfq_set_active_queue(struct cfq_data *cfqd, */ static void __cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq, - bool timed_out) + bool timed_out, bool forced) { cfq_log_cfqq(cfqd, cfqq, "slice expired t=%d", timed_out); if (cfq_cfqq_wait_request(cfqq)) - del_timer(&cfqd->idle_slice_timer); + cfq_del_timer(cfqd, cfqq); cfq_clear_cfqq_wait_request(cfqq); cfq_clear_cfqq_wait_busy(cfqq); @@ -1577,7 +1598,7 @@ __cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq, cfq_log_cfqq(cfqd, cfqq, "resid=%ld", cfqq->slice_resid); } - cfq_group_served(cfqd, cfqq->cfqg, cfqq); + cfq_group_served(cfqd, cfqq->cfqg, cfqq, forced); if (cfq_cfqq_on_rr(cfqq) && RB_EMPTY_ROOT(&cfqq->sort_list)) cfq_del_cfqq_rr(cfqd, cfqq); @@ -1596,12 +1617,13 @@ __cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq, } } -static inline void cfq_slice_expired(struct cfq_data *cfqd, bool timed_out) +static inline void cfq_slice_expired(struct cfq_data *cfqd, bool timed_out, + bool forced) { struct cfq_queue *cfqq = cfqd->active_queue; if (cfqq) - __cfq_slice_expired(cfqd, cfqq, timed_out); + __cfq_slice_expired(cfqd, cfqq, timed_out, forced); } /* @@ -1857,6 +1879,7 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd) sl = cfqd->cfq_slice_idle; mod_timer(&cfqd->idle_slice_timer, jiffies + sl); + blkiocg_update_set_idle_time_stats(&cfqq->cfqg->blkg); cfq_log_cfqq(cfqd, cfqq, "arm_idle: %lu", sl); } @@ -1876,7 +1899,8 @@ static void cfq_dispatch_insert(struct request_queue *q, struct request *rq) elv_dispatch_sort(q, rq); cfqd->rq_in_flight[cfq_cfqq_sync(cfqq)]++; - cfqq->nr_sectors += blk_rq_sectors(rq); + blkiocg_update_dispatch_stats(&cfqq->cfqg->blkg, blk_rq_bytes(rq), + rq_data_dir(rq), rq_is_sync(rq)); } /* @@ -2167,7 +2191,7 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd) } expire: - cfq_slice_expired(cfqd, 0); + cfq_slice_expired(cfqd, 0, false); new_queue: /* * Current queue expired. Check if we have to switch to a new @@ -2193,7 +2217,7 @@ static int __cfq_forced_dispatch_cfqq(struct cfq_queue *cfqq) BUG_ON(!list_empty(&cfqq->fifo)); /* By default cfqq is not expired if it is empty. Do it explicitly */ - __cfq_slice_expired(cfqq->cfqd, cfqq, 0); + __cfq_slice_expired(cfqq->cfqd, cfqq, 0, true); return dispatched; } @@ -2376,7 +2400,7 @@ static int cfq_dispatch_requests(struct request_queue *q, int force) cfqq->slice_dispatch >= cfq_prio_to_maxrq(cfqd, cfqq)) || cfq_class_idle(cfqq))) { cfqq->slice_end = jiffies + 1; - cfq_slice_expired(cfqd, 0); + cfq_slice_expired(cfqd, 0, false); } cfq_log_cfqq(cfqd, cfqq, "dispatched a request"); @@ -2407,7 +2431,7 @@ static void cfq_put_queue(struct cfq_queue *cfqq) orig_cfqg = cfqq->orig_cfqg; if (unlikely(cfqd->active_queue == cfqq)) { - __cfq_slice_expired(cfqd, cfqq, 0); + __cfq_slice_expired(cfqd, cfqq, 0, false); cfq_schedule_dispatch(cfqd); } @@ -2508,7 +2532,7 @@ static void cfq_exit_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq) struct cfq_queue *__cfqq, *next; if (unlikely(cfqq == cfqd->active_queue)) { - __cfq_slice_expired(cfqd, cfqq, 0); + __cfq_slice_expired(cfqd, cfqq, 0, false); cfq_schedule_dispatch(cfqd); } @@ -3137,7 +3161,7 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq, static void cfq_preempt_queue(struct cfq_data *cfqd, struct cfq_queue *cfqq) { cfq_log_cfqq(cfqd, cfqq, "preempt"); - cfq_slice_expired(cfqd, 1); + cfq_slice_expired(cfqd, 1, false); /* * Put the new queue at the front of the of the current list, @@ -3185,11 +3209,14 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq, if (cfq_cfqq_wait_request(cfqq)) { if (blk_rq_bytes(rq) > PAGE_CACHE_SIZE || cfqd->busy_queues > 1) { - del_timer(&cfqd->idle_slice_timer); + cfq_del_timer(cfqd, cfqq); cfq_clear_cfqq_wait_request(cfqq); __blk_run_queue(cfqd->queue); - } else + } else { + blkiocg_update_idle_time_stats( + &cfqq->cfqg->blkg); cfq_mark_cfqq_must_dispatch(cfqq); + } } } else if (cfq_should_preempt(cfqd, cfqq, rq)) { /* @@ -3215,6 +3242,9 @@ static void cfq_insert_request(struct request_queue *q, struct request *rq) list_add_tail(&rq->queuelist, &cfqq->fifo); cfq_add_rq_rb(rq); + blkiocg_update_io_add_stats(&cfqq->cfqg->blkg, + &cfqd->serving_group->blkg, rq_data_dir(rq), + rq_is_sync(rq)); cfq_rq_enqueued(cfqd, cfqq, rq); } @@ -3300,6 +3330,9 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq) WARN_ON(!cfqq->dispatched); cfqd->rq_in_driver--; cfqq->dispatched--; + blkiocg_update_completion_stats(&cfqq->cfqg->blkg, rq_start_time_ns(rq), + rq_io_start_time_ns(rq), rq_data_dir(rq), + rq_is_sync(rq)); cfqd->rq_in_flight[cfq_cfqq_sync(cfqq)]--; @@ -3340,7 +3373,7 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq) * - when there is a close cooperator */ if (cfq_slice_used(cfqq) || cfq_class_idle(cfqq)) - cfq_slice_expired(cfqd, 1); + cfq_slice_expired(cfqd, 1, false); else if (sync && cfqq_empty && !cfq_close_cooperator(cfqd, cfqq)) { cfqd->noidle_tree_requires_idle |= !rq_noidle(rq); @@ -3600,7 +3633,7 @@ static void cfq_idle_slice_timer(unsigned long data) cfq_clear_cfqq_deep(cfqq); } expire: - cfq_slice_expired(cfqd, timed_out); + cfq_slice_expired(cfqd, timed_out, false); out_kick: cfq_schedule_dispatch(cfqd); out_cont: @@ -3643,7 +3676,7 @@ static void cfq_exit_queue(struct elevator_queue *e) spin_lock_irq(q->queue_lock); if (cfqd->active_queue) - __cfq_slice_expired(cfqd, cfqd->active_queue, 0); + __cfq_slice_expired(cfqd, cfqd->active_queue, 0, false); while (!list_empty(&cfqd->cic_list)) { struct cfq_io_context *cic = list_entry(cfqd->cic_list.next, @@ -3870,6 +3903,7 @@ static struct elevator_type iosched_cfq = { .elevator_merged_fn = cfq_merged_request, .elevator_merge_req_fn = cfq_merged_requests, .elevator_allow_merge_fn = cfq_allow_merge, + .elevator_bio_merged_fn = cfq_bio_merged, .elevator_dispatch_fn = cfq_dispatch_requests, .elevator_add_req_fn = cfq_insert_request, .elevator_activate_req_fn = cfq_activate_request, diff --git a/block/elevator.c b/block/elevator.c index 76e3702..5e73459 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -539,6 +539,15 @@ void elv_merge_requests(struct request_queue *q, struct request *rq, q->last_merge = rq; } +void elv_bio_merged(struct request_queue *q, struct request *rq, + struct bio *bio) +{ + struct elevator_queue *e = q->elevator; + + if (e->ops->elevator_bio_merged_fn) + e->ops->elevator_bio_merged_fn(q, rq, bio); +} + void elv_requeue_request(struct request_queue *q, struct request *rq) { /* diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index fcbc26a..2742e1a 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -14,6 +14,7 @@ #include <linux/kernel.h> #include <linux/fs.h> #include <linux/sched.h> +#include <linux/timer.h> #include <linux/writeback.h> #include <asm/atomic.h> @@ -88,6 +89,8 @@ struct backing_dev_info { struct device *dev; + struct timer_list laptop_mode_wb_timer; + #ifdef CONFIG_DEBUG_FS struct dentry *debug_dir; struct dentry *debug_stats; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6690e8b..d483c49 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -194,7 +194,10 @@ struct request { struct gendisk *rq_disk; unsigned long start_time; - +#ifdef CONFIG_BLK_CGROUP + unsigned long long start_time_ns; + unsigned long long io_start_time_ns; /* when passed to hardware */ +#endif /* Number of scatter-gather DMA addr+len pairs after * physical address coalescing is performed. */ @@ -1196,6 +1199,39 @@ static inline void put_dev_sector(Sector p) struct work_struct; int kblockd_schedule_work(struct request_queue *q, struct work_struct *work); +#ifdef CONFIG_BLK_CGROUP +static inline void set_start_time_ns(struct request *req) +{ + req->start_time_ns = sched_clock(); +} + +static inline void set_io_start_time_ns(struct request *req) +{ + req->io_start_time_ns = sched_clock(); +} + +static inline uint64_t rq_start_time_ns(struct request *req) +{ + return req->start_time_ns; +} + +static inline uint64_t rq_io_start_time_ns(struct request *req) +{ + return req->io_start_time_ns; +} +#else +static inline void set_start_time_ns(struct request *req) {} +static inline void set_io_start_time_ns(struct request *req) {} +static inline uint64_t rq_start_time_ns(struct request *req) +{ + return 0; +} +static inline uint64_t rq_io_start_time_ns(struct request *req) +{ + return 0; +} +#endif + #define MODULE_ALIAS_BLOCKDEV(major,minor) \ MODULE_ALIAS("block-major-" __stringify(major) "-" __stringify(minor)) #define MODULE_ALIAS_BLOCKDEV_MAJOR(major) \ diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 1cb3372e..2c958f4 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -14,6 +14,9 @@ typedef void (elevator_merged_fn) (struct request_queue *, struct request *, int typedef int (elevator_allow_merge_fn) (struct request_queue *, struct request *, struct bio *); +typedef void (elevator_bio_merged_fn) (struct request_queue *, + struct request *, struct bio *); + typedef int (elevator_dispatch_fn) (struct request_queue *, int); typedef void (elevator_add_req_fn) (struct request_queue *, struct request *); @@ -36,6 +39,7 @@ struct elevator_ops elevator_merged_fn *elevator_merged_fn; elevator_merge_req_fn *elevator_merge_req_fn; elevator_allow_merge_fn *elevator_allow_merge_fn; + elevator_bio_merged_fn *elevator_bio_merged_fn; elevator_dispatch_fn *elevator_dispatch_fn; elevator_add_req_fn *elevator_add_req_fn; @@ -103,6 +107,8 @@ extern int elv_merge(struct request_queue *, struct request **, struct bio *); extern void elv_merge_requests(struct request_queue *, struct request *, struct request *); extern void elv_merged_request(struct request_queue *, struct request *, int); +extern void elv_bio_merged(struct request_queue *q, struct request *, + struct bio *); extern void elv_requeue_request(struct request_queue *, struct request *); extern int elv_queue_empty(struct request_queue *); extern struct request *elv_former_request(struct request_queue *, struct request *); diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 36520de..eb38a2c 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -96,8 +96,10 @@ static inline void inode_sync_wait(struct inode *inode) /* * mm/page-writeback.c */ -void laptop_io_completion(void); +void laptop_io_completion(struct backing_dev_info *info); void laptop_sync_completion(void); +void laptop_mode_sync(struct work_struct *work); +void laptop_mode_timer_fn(unsigned long data); void throttle_vm_writeout(gfp_t gfp_mask); /* These are exported to sysctl. */ diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 0b19943..d0f2b37 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -683,10 +683,6 @@ void throttle_vm_writeout(gfp_t gfp_mask) } } -static void laptop_timer_fn(unsigned long unused); - -static DEFINE_TIMER(laptop_mode_wb_timer, laptop_timer_fn, 0, 0); - /* * sysctl handler for /proc/sys/vm/dirty_writeback_centisecs */ @@ -697,21 +693,19 @@ int dirty_writeback_centisecs_handler(ctl_table *table, int write, return 0; } -static void do_laptop_sync(struct work_struct *work) +void laptop_mode_timer_fn(unsigned long data) { - wakeup_flusher_threads(0); - kfree(work); -} + struct request_queue *q = (struct request_queue *)data; + int nr_pages = global_page_state(NR_FILE_DIRTY) + + global_page_state(NR_UNSTABLE_NFS); -static void laptop_timer_fn(unsigned long unused) -{ - struct work_struct *work; + /* + * We want to write everything out, not just down to the dirty + * threshold + */ - work = kmalloc(sizeof(*work), GFP_ATOMIC); - if (work) { - INIT_WORK(work, do_laptop_sync); - schedule_work(work); - } + if (bdi_has_dirty_io(&q->backing_dev_info)) + bdi_start_writeback(&q->backing_dev_info, NULL, nr_pages); } /* @@ -719,9 +713,9 @@ static void laptop_timer_fn(unsigned long unused) * of all dirty data a few seconds from now. If the flush is already scheduled * then push it back - the user is still using the disk. */ -void laptop_io_completion(void) +void laptop_io_completion(struct backing_dev_info *info) { - mod_timer(&laptop_mode_wb_timer, jiffies + laptop_mode); + mod_timer(&info->laptop_mode_wb_timer, jiffies + laptop_mode); } /* @@ -731,7 +725,14 @@ void laptop_io_completion(void) */ void laptop_sync_completion(void) { - del_timer(&laptop_mode_wb_timer); + struct backing_dev_info *bdi; + + rcu_read_lock(); + + list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) + del_timer(&bdi->laptop_mode_wb_timer); + + rcu_read_unlock(); } /* |