#define DFL_THROTL_SLICE_HD (HZ / 10)
#define DFL_THROTL_SLICE_SSD (HZ / 50)
#define MAX_THROTL_SLICE (HZ)
-#define MAX_IDLE_TIME (5L * 1000 * 1000) /* 5 s */
-#define MIN_THROTL_BPS (320 * 1024)
-#define MIN_THROTL_IOPS (10)
-#define DFL_LATENCY_TARGET (-1L)
-#define DFL_IDLE_THRESHOLD (0)
-#define DFL_HD_BASELINE_LATENCY (4000L) /* 4ms */
-#define LATENCY_FILTERED_SSD (0)
-/*
- * For HD, very small latency comes from sequential IO. Such IO is helpless to
- * help determine if its IO is impacted by others, hence we ignore the IO
- */
-#define LATENCY_FILTERED_HD (1000L) /* 1ms */
/* A workqueue to queue throttle related work */
static struct workqueue_struct *kthrotld_workqueue;
int samples;
};
-struct avg_latency_bucket {
- unsigned long latency; /* ns / 1024 */
- bool valid;
-};
-
struct throtl_data
{
/* service tree for active throtl groups */
/* Work for dispatching throttled bios */
struct work_struct dispatch_work;
- unsigned int limit_index;
- bool limit_valid[LIMIT_CNT];
-
- unsigned long low_upgrade_time;
- unsigned long low_downgrade_time;
-
- unsigned int scale;
-
- struct latency_bucket tmp_buckets[2][LATENCY_BUCKET_SIZE];
- struct avg_latency_bucket avg_buckets[2][LATENCY_BUCKET_SIZE];
- struct latency_bucket __percpu *latency_buckets[2];
- unsigned long last_calculate_time;
- unsigned long filtered_latency;
bool track_bio_latency;
};
return container_of(sq, struct throtl_data, service_queue);
}
-/*
- * cgroup's limit in LIMIT_MAX is scaled if low limit is set. This scale is to
- * make the IO dispatch more smooth.
- * Scale up: linearly scale up according to elapsed time since upgrade. For
- * every throtl_slice, the limit scales up 1/2 .low limit till the
- * limit hits .max limit
- * Scale down: exponentially scale down if a cgroup doesn't hit its .low limit
- */
-static uint64_t throtl_adjusted_limit(uint64_t low, struct throtl_data *td)
-{
- /* arbitrary value to avoid too big scale */
- if (td->scale < 4096 && time_after_eq(jiffies,
- td->low_upgrade_time + td->scale * td->throtl_slice))
- td->scale = (jiffies - td->low_upgrade_time) / td->throtl_slice;
-
- return low + (low >> 1) * td->scale;
-}
-
static uint64_t tg_bps_limit(struct throtl_grp *tg, int rw)
{
struct blkcg_gq *blkg = tg_to_blkg(tg);
- struct throtl_data *td;
- uint64_t ret;
if (cgroup_subsys_on_dfl(io_cgrp_subsys) && !blkg->parent)
return U64_MAX;
- td = tg->td;
- ret = tg->bps[rw][td->limit_index];
- if (ret == 0 && td->limit_index == LIMIT_LOW) {
- /* intermediate node or iops isn't 0 */
- if (!list_empty(&blkg->blkcg->css.children) ||
- tg->iops[rw][td->limit_index])
- return U64_MAX;
- else
- return MIN_THROTL_BPS;
- }
-
- if (td->limit_index == LIMIT_MAX && tg->bps[rw][LIMIT_LOW] &&
- tg->bps[rw][LIMIT_LOW] != tg->bps[rw][LIMIT_MAX]) {
- uint64_t adjusted;
-
- adjusted = throtl_adjusted_limit(tg->bps[rw][LIMIT_LOW], td);
- ret = min(tg->bps[rw][LIMIT_MAX], adjusted);
- }
- return ret;
+ return tg->bps[rw];
}
static unsigned int tg_iops_limit(struct throtl_grp *tg, int rw)
{
struct blkcg_gq *blkg = tg_to_blkg(tg);
- struct throtl_data *td;
- unsigned int ret;
if (cgroup_subsys_on_dfl(io_cgrp_subsys) && !blkg->parent)
return UINT_MAX;
- td = tg->td;
- ret = tg->iops[rw][td->limit_index];
- if (ret == 0 && tg->td->limit_index == LIMIT_LOW) {
- /* intermediate node or bps isn't 0 */
- if (!list_empty(&blkg->blkcg->css.children) ||
- tg->bps[rw][td->limit_index])
- return UINT_MAX;
- else
- return MIN_THROTL_IOPS;
- }
-
- if (td->limit_index == LIMIT_MAX && tg->iops[rw][LIMIT_LOW] &&
- tg->iops[rw][LIMIT_LOW] != tg->iops[rw][LIMIT_MAX]) {
- uint64_t adjusted;
-
- adjusted = throtl_adjusted_limit(tg->iops[rw][LIMIT_LOW], td);
- if (adjusted > UINT_MAX)
- adjusted = UINT_MAX;
- ret = min_t(unsigned int, tg->iops[rw][LIMIT_MAX], adjusted);
- }
- return ret;
+ return tg->iops[rw];
}
#define request_bucket_index(sectors) \
}
RB_CLEAR_NODE(&tg->rb_node);
- tg->bps[READ][LIMIT_MAX] = U64_MAX;
- tg->bps[WRITE][LIMIT_MAX] = U64_MAX;
- tg->iops[READ][LIMIT_MAX] = UINT_MAX;
- tg->iops[WRITE][LIMIT_MAX] = UINT_MAX;
- tg->bps_conf[READ][LIMIT_MAX] = U64_MAX;
- tg->bps_conf[WRITE][LIMIT_MAX] = U64_MAX;
- tg->iops_conf[READ][LIMIT_MAX] = UINT_MAX;
- tg->iops_conf[WRITE][LIMIT_MAX] = UINT_MAX;
- /* LIMIT_LOW will have default value 0 */
-
- tg->latency_target = DFL_LATENCY_TARGET;
- tg->latency_target_conf = DFL_LATENCY_TARGET;
- tg->idletime_threshold = DFL_IDLE_THRESHOLD;
- tg->idletime_threshold_conf = DFL_IDLE_THRESHOLD;
+ tg->bps[READ] = U64_MAX;
+ tg->bps[WRITE] = U64_MAX;
+ tg->iops[READ] = UINT_MAX;
+ tg->iops[WRITE] = UINT_MAX;
return &tg->pd;
static void tg_update_has_rules(struct throtl_grp *tg)
{
struct throtl_grp *parent_tg = sq_to_tg(tg->service_queue.parent_sq);
- struct throtl_data *td = tg->td;
int rw;
for (rw = READ; rw <= WRITE; rw++) {
tg->has_rules_iops[rw] =
(parent_tg && parent_tg->has_rules_iops[rw]) ||
- (td->limit_valid[td->limit_index] &&
- tg_iops_limit(tg, rw) != UINT_MAX);
+ tg_iops_limit(tg, rw) != UINT_MAX;
tg->has_rules_bps[rw] =
(parent_tg && parent_tg->has_rules_bps[rw]) ||
- (td->limit_valid[td->limit_index] &&
- (tg_bps_limit(tg, rw) != U64_MAX));
+ tg_bps_limit(tg, rw) != U64_MAX;
}
}
tg_update_has_rules(tg);
}
-#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
-static void blk_throtl_update_limit_valid(struct throtl_data *td)
-{
- struct cgroup_subsys_state *pos_css;
- struct blkcg_gq *blkg;
- bool low_valid = false;
-
- rcu_read_lock();
- blkg_for_each_descendant_post(blkg, pos_css, td->queue->root_blkg) {
- struct throtl_grp *tg = blkg_to_tg(blkg);
-
- if (tg->bps[READ][LIMIT_LOW] || tg->bps[WRITE][LIMIT_LOW] ||
- tg->iops[READ][LIMIT_LOW] || tg->iops[WRITE][LIMIT_LOW]) {
- low_valid = true;
- break;
- }
- }
- rcu_read_unlock();
-
- td->limit_valid[LIMIT_LOW] = low_valid;
-}
-#else
-static inline void blk_throtl_update_limit_valid(struct throtl_data *td)
-{
-}
-#endif
-
-static void throtl_upgrade_state(struct throtl_data *td);
-static void throtl_pd_offline(struct blkg_policy_data *pd)
-{
- struct throtl_grp *tg = pd_to_tg(pd);
-
- tg->bps[READ][LIMIT_LOW] = 0;
- tg->bps[WRITE][LIMIT_LOW] = 0;
- tg->iops[READ][LIMIT_LOW] = 0;
- tg->iops[WRITE][LIMIT_LOW] = 0;
-
- blk_throtl_update_limit_valid(tg->td);
-
- if (!tg->td->limit_valid[tg->td->limit_index])
- throtl_upgrade_state(tg->td);
-}
-
static void throtl_pd_free(struct blkg_policy_data *pd)
{
struct throtl_grp *tg = pd_to_tg(pd);
/* Calc approx time to dispatch */
jiffy_wait = jiffy_elapsed_rnd - jiffy_elapsed;
+
+ /* make sure at least one io can be dispatched after waiting */
+ jiffy_wait = max(jiffy_wait, HZ / iops_limit + 1);
return jiffy_wait;
}
return nr_disp;
}
-static bool throtl_can_upgrade(struct throtl_data *td,
- struct throtl_grp *this_tg);
/**
* throtl_pending_timer_fn - timer function for service_queue->pending_timer
* @t: the pending_timer member of the throtl_service_queue being serviced
if (!q->root_blkg)
goto out_unlock;
- if (throtl_can_upgrade(td, NULL))
- throtl_upgrade_state(td);
-
again:
parent_sq = sq->parent_sq;
dispatched = false;
blkg_for_each_descendant_pre(blkg, pos_css,
global ? tg->td->queue->root_blkg : tg_to_blkg(tg)) {
struct throtl_grp *this_tg = blkg_to_tg(blkg);
- struct throtl_grp *parent_tg;
tg_update_has_rules(this_tg);
/* ignore root/second level */
if (!cgroup_subsys_on_dfl(io_cgrp_subsys) || !blkg->parent ||
!blkg->parent->parent)
continue;
- parent_tg = blkg_to_tg(blkg->parent);
- /*
- * make sure all children has lower idle time threshold and
- * higher latency target
- */
- this_tg->idletime_threshold = min(this_tg->idletime_threshold,
- parent_tg->idletime_threshold);
- this_tg->latency_target = max(this_tg->latency_target,
- parent_tg->latency_target);
}
rcu_read_unlock();
}
}
+static int blk_throtl_init(struct gendisk *disk)
+{
+ struct request_queue *q = disk->queue;
+ struct throtl_data *td;
+ int ret;
+
+ td = kzalloc_node(sizeof(*td), GFP_KERNEL, q->node);
+ if (!td)
+ return -ENOMEM;
+
+ INIT_WORK(&td->dispatch_work, blk_throtl_dispatch_work_fn);
+ throtl_service_queue_init(&td->service_queue);
+
+ /*
+ * Freeze queue before activating policy, to synchronize with IO path,
+ * which is protected by 'q_usage_counter'.
+ */
+ blk_mq_freeze_queue(disk->queue);
+ blk_mq_quiesce_queue(disk->queue);
+
+ q->td = td;
+ td->queue = q;
+
+ /* activate policy */
+ ret = blkcg_activate_policy(disk, &blkcg_policy_throtl);
+ if (ret) {
+ q->td = NULL;
+ kfree(td);
+ goto out;
+ }
+
+ if (blk_queue_nonrot(q))
+ td->throtl_slice = DFL_THROTL_SLICE_SSD;
+ else
+ td->throtl_slice = DFL_THROTL_SLICE_HD;
+ td->track_bio_latency = !queue_is_mq(q);
+ if (!td->track_bio_latency)
+ blk_stat_enable_accounting(q);
+
+out:
+ blk_mq_unquiesce_queue(disk->queue);
+ blk_mq_unfreeze_queue(disk->queue);
+
+ return ret;
+}
+
+
static ssize_t tg_set_conf(struct kernfs_open_file *of,
char *buf, size_t nbytes, loff_t off, bool is_u64)
{
blkg_conf_init(&ctx, buf);
+ ret = blkg_conf_open_bdev(&ctx);
+ if (ret)
+ goto out_finish;
+
+ if (!blk_throtl_activated(ctx.bdev->bd_queue)) {
+ ret = blk_throtl_init(ctx.bdev->bd_disk);
+ if (ret)
+ goto out_finish;
+ }
+
ret = blkg_conf_prep(blkcg, &blkcg_policy_throtl, &ctx);
if (ret)
goto out_finish;
static struct cftype throtl_legacy_files[] = {
{
.name = "throttle.read_bps_device",
- .private = offsetof(struct throtl_grp, bps[READ][LIMIT_MAX]),
+ .private = offsetof(struct throtl_grp, bps[READ]),
.seq_show = tg_print_conf_u64,
.write = tg_set_conf_u64,
},
{
.name = "throttle.write_bps_device",
- .private = offsetof(struct throtl_grp, bps[WRITE][LIMIT_MAX]),
+ .private = offsetof(struct throtl_grp, bps[WRITE]),
.seq_show = tg_print_conf_u64,
.write = tg_set_conf_u64,
},
{
.name = "throttle.read_iops_device",
- .private = offsetof(struct throtl_grp, iops[READ][LIMIT_MAX]),
+ .private = offsetof(struct throtl_grp, iops[READ]),
.seq_show = tg_print_conf_uint,
.write = tg_set_conf_uint,
},
{
.name = "throttle.write_iops_device",
- .private = offsetof(struct throtl_grp, iops[WRITE][LIMIT_MAX]),
+ .private = offsetof(struct throtl_grp, iops[WRITE]),
.seq_show = tg_print_conf_uint,
.write = tg_set_conf_uint,
},
{
struct throtl_grp *tg = pd_to_tg(pd);
const char *dname = blkg_dev_name(pd->blkg);
- char bufs[4][21] = { "max", "max", "max", "max" };
u64 bps_dft;
unsigned int iops_dft;
- char idle_time[26] = "";
- char latency_time[26] = "";
if (!dname)
return 0;
- if (off == LIMIT_LOW) {
- bps_dft = 0;
- iops_dft = 0;
- } else {
- bps_dft = U64_MAX;
- iops_dft = UINT_MAX;
- }
+ bps_dft = U64_MAX;
+ iops_dft = UINT_MAX;
- if (tg->bps_conf[READ][off] == bps_dft &&
- tg->bps_conf[WRITE][off] == bps_dft &&
- tg->iops_conf[READ][off] == iops_dft &&
- tg->iops_conf[WRITE][off] == iops_dft &&
- (off != LIMIT_LOW ||
- (tg->idletime_threshold_conf == DFL_IDLE_THRESHOLD &&
- tg->latency_target_conf == DFL_LATENCY_TARGET)))
+ if (tg->bps[READ] == bps_dft &&
+ tg->bps[WRITE] == bps_dft &&
+ tg->iops[READ] == iops_dft &&
+ tg->iops[WRITE] == iops_dft)
return 0;
- if (tg->bps_conf[READ][off] != U64_MAX)
- snprintf(bufs[0], sizeof(bufs[0]), "%llu",
- tg->bps_conf[READ][off]);
- if (tg->bps_conf[WRITE][off] != U64_MAX)
- snprintf(bufs[1], sizeof(bufs[1]), "%llu",
- tg->bps_conf[WRITE][off]);
- if (tg->iops_conf[READ][off] != UINT_MAX)
- snprintf(bufs[2], sizeof(bufs[2]), "%u",
- tg->iops_conf[READ][off]);
- if (tg->iops_conf[WRITE][off] != UINT_MAX)
- snprintf(bufs[3], sizeof(bufs[3]), "%u",
- tg->iops_conf[WRITE][off]);
- if (off == LIMIT_LOW) {
- if (tg->idletime_threshold_conf == ULONG_MAX)
- strcpy(idle_time, " idle=max");
- else
- snprintf(idle_time, sizeof(idle_time), " idle=%lu",
- tg->idletime_threshold_conf);
+ seq_printf(sf, "%s", dname);
+ if (tg->bps[READ] == U64_MAX)
+ seq_printf(sf, " rbps=max");
+ else
+ seq_printf(sf, " rbps=%llu", tg->bps[READ]);
- if (tg->latency_target_conf == ULONG_MAX)
- strcpy(latency_time, " latency=max");
- else
- snprintf(latency_time, sizeof(latency_time),
- " latency=%lu", tg->latency_target_conf);
- }
+ if (tg->bps[WRITE] == U64_MAX)
+ seq_printf(sf, " wbps=max");
+ else
+ seq_printf(sf, " wbps=%llu", tg->bps[WRITE]);
+
+ if (tg->iops[READ] == UINT_MAX)
+ seq_printf(sf, " riops=max");
+ else
+ seq_printf(sf, " riops=%u", tg->iops[READ]);
+
+ if (tg->iops[WRITE] == UINT_MAX)
+ seq_printf(sf, " wiops=max");
+ else
+ seq_printf(sf, " wiops=%u", tg->iops[WRITE]);
- seq_printf(sf, "%s rbps=%s wbps=%s riops=%s wiops=%s%s%s\n",
- dname, bufs[0], bufs[1], bufs[2], bufs[3], idle_time,
- latency_time);
+ seq_printf(sf, "\n");
return 0;
}
struct blkg_conf_ctx ctx;
struct throtl_grp *tg;
u64 v[4];
- unsigned long idle_time;
- unsigned long latency_time;
int ret;
- int index = of_cft(of)->private;
blkg_conf_init(&ctx, buf);
+ ret = blkg_conf_open_bdev(&ctx);
+ if (ret)
+ goto out_finish;
+
+ if (!blk_throtl_activated(ctx.bdev->bd_queue)) {
+ ret = blk_throtl_init(ctx.bdev->bd_disk);
+ if (ret)
+ goto out_finish;
+ }
+
ret = blkg_conf_prep(blkcg, &blkcg_policy_throtl, &ctx);
if (ret)
goto out_finish;
tg = blkg_to_tg(ctx.blkg);
tg_update_carryover(tg);
- v[0] = tg->bps_conf[READ][index];
- v[1] = tg->bps_conf[WRITE][index];
- v[2] = tg->iops_conf[READ][index];
- v[3] = tg->iops_conf[WRITE][index];
+ v[0] = tg->bps[READ];
+ v[1] = tg->bps[WRITE];
+ v[2] = tg->iops[READ];
+ v[3] = tg->iops[WRITE];
- idle_time = tg->idletime_threshold_conf;
- latency_time = tg->latency_target_conf;
while (true) {
char tok[27]; /* wiops=18446744073709551616 */
char *p;
v[2] = min_t(u64, val, UINT_MAX);
else if (!strcmp(tok, "wiops") && val > 1)
v[3] = min_t(u64, val, UINT_MAX);
- else if (off == LIMIT_LOW && !strcmp(tok, "idle"))
- idle_time = val;
- else if (off == LIMIT_LOW && !strcmp(tok, "latency"))
- latency_time = val;
else
goto out_finish;
}
- tg->bps_conf[READ][index] = v[0];
- tg->bps_conf[WRITE][index] = v[1];
- tg->iops_conf[READ][index] = v[2];
- tg->iops_conf[WRITE][index] = v[3];
+ tg->bps[READ] = v[0];
+ tg->bps[WRITE] = v[1];
+ tg->iops[READ] = v[2];
+ tg->iops[WRITE] = v[3];
- if (index == LIMIT_MAX) {
- tg->bps[READ][index] = v[0];
- tg->bps[WRITE][index] = v[1];
- tg->iops[READ][index] = v[2];
- tg->iops[WRITE][index] = v[3];
- }
- tg->bps[READ][LIMIT_LOW] = min(tg->bps_conf[READ][LIMIT_LOW],
- tg->bps_conf[READ][LIMIT_MAX]);
- tg->bps[WRITE][LIMIT_LOW] = min(tg->bps_conf[WRITE][LIMIT_LOW],
- tg->bps_conf[WRITE][LIMIT_MAX]);
- tg->iops[READ][LIMIT_LOW] = min(tg->iops_conf[READ][LIMIT_LOW],
- tg->iops_conf[READ][LIMIT_MAX]);
- tg->iops[WRITE][LIMIT_LOW] = min(tg->iops_conf[WRITE][LIMIT_LOW],
- tg->iops_conf[WRITE][LIMIT_MAX]);
- tg->idletime_threshold_conf = idle_time;
- tg->latency_target_conf = latency_time;
-
- /* force user to configure all settings for low limit */
- if (!(tg->bps[READ][LIMIT_LOW] || tg->iops[READ][LIMIT_LOW] ||
- tg->bps[WRITE][LIMIT_LOW] || tg->iops[WRITE][LIMIT_LOW]) ||
- tg->idletime_threshold_conf == DFL_IDLE_THRESHOLD ||
- tg->latency_target_conf == DFL_LATENCY_TARGET) {
- tg->bps[READ][LIMIT_LOW] = 0;
- tg->bps[WRITE][LIMIT_LOW] = 0;
- tg->iops[READ][LIMIT_LOW] = 0;
- tg->iops[WRITE][LIMIT_LOW] = 0;
- tg->idletime_threshold = DFL_IDLE_THRESHOLD;
- tg->latency_target = DFL_LATENCY_TARGET;
- } else if (index == LIMIT_LOW) {
- tg->idletime_threshold = tg->idletime_threshold_conf;
- tg->latency_target = tg->latency_target_conf;
- }
-
- blk_throtl_update_limit_valid(tg->td);
- if (tg->td->limit_valid[LIMIT_LOW]) {
- if (index == LIMIT_LOW)
- tg->td->limit_index = LIMIT_LOW;
- } else
- tg->td->limit_index = LIMIT_MAX;
- tg_conf_updated(tg, index == LIMIT_LOW &&
- tg->td->limit_valid[LIMIT_LOW]);
+ tg_conf_updated(tg, false);
ret = 0;
out_finish:
blkg_conf_exit(&ctx);
}
static struct cftype throtl_files[] = {
-#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
- {
- .name = "low",
- .flags = CFTYPE_NOT_ON_ROOT,
- .seq_show = tg_print_limit,
- .write = tg_set_limit,
- .private = LIMIT_LOW,
- },
-#endif
{
.name = "max",
.flags = CFTYPE_NOT_ON_ROOT,
.seq_show = tg_print_limit,
.write = tg_set_limit,
- .private = LIMIT_MAX,
},
{ } /* terminate */
};
.pd_alloc_fn = throtl_pd_alloc,
.pd_init_fn = throtl_pd_init,
.pd_online_fn = throtl_pd_online,
- .pd_offline_fn = throtl_pd_offline,
.pd_free_fn = throtl_pd_free,
};
struct cgroup_subsys_state *pos_css;
struct blkcg_gq *blkg;
+ if (!blk_throtl_activated(q))
+ return;
+
spin_lock_irq(&q->queue_lock);
/*
* queue_lock is held, rcu lock is not needed here technically.
spin_unlock_irq(&q->queue_lock);
}
-#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
-static unsigned long __tg_last_low_overflow_time(struct throtl_grp *tg)
-{
- unsigned long rtime = jiffies, wtime = jiffies;
-
- if (tg->bps[READ][LIMIT_LOW] || tg->iops[READ][LIMIT_LOW])
- rtime = tg->last_low_overflow_time[READ];
- if (tg->bps[WRITE][LIMIT_LOW] || tg->iops[WRITE][LIMIT_LOW])
- wtime = tg->last_low_overflow_time[WRITE];
- return min(rtime, wtime);
-}
-
-static unsigned long tg_last_low_overflow_time(struct throtl_grp *tg)
-{
- struct throtl_service_queue *parent_sq;
- struct throtl_grp *parent = tg;
- unsigned long ret = __tg_last_low_overflow_time(tg);
-
- while (true) {
- parent_sq = parent->service_queue.parent_sq;
- parent = sq_to_tg(parent_sq);
- if (!parent)
- break;
-
- /*
- * The parent doesn't have low limit, it always reaches low
- * limit. Its overflow time is useless for children
- */
- if (!parent->bps[READ][LIMIT_LOW] &&
- !parent->iops[READ][LIMIT_LOW] &&
- !parent->bps[WRITE][LIMIT_LOW] &&
- !parent->iops[WRITE][LIMIT_LOW])
- continue;
- if (time_after(__tg_last_low_overflow_time(parent), ret))
- ret = __tg_last_low_overflow_time(parent);
- }
- return ret;
-}
-
-static bool throtl_tg_is_idle(struct throtl_grp *tg)
-{
- /*
- * cgroup is idle if:
- * - single idle is too long, longer than a fixed value (in case user
- * configure a too big threshold) or 4 times of idletime threshold
- * - average think time is more than threshold
- * - IO latency is largely below threshold
- */
- unsigned long time;
- bool ret;
-
- time = min_t(unsigned long, MAX_IDLE_TIME, 4 * tg->idletime_threshold);
- ret = tg->latency_target == DFL_LATENCY_TARGET ||
- tg->idletime_threshold == DFL_IDLE_THRESHOLD ||
- (blk_time_get_ns() >> 10) - tg->last_finish_time > time ||
- tg->avg_idletime > tg->idletime_threshold ||
- (tg->latency_target && tg->bio_cnt &&
- tg->bad_bio_cnt * 5 < tg->bio_cnt);
- throtl_log(&tg->service_queue,
- "avg_idle=%ld, idle_threshold=%ld, bad_bio=%d, total_bio=%d, is_idle=%d, scale=%d",
- tg->avg_idletime, tg->idletime_threshold, tg->bad_bio_cnt,
- tg->bio_cnt, ret, tg->td->scale);
- return ret;
-}
-
-static bool throtl_low_limit_reached(struct throtl_grp *tg, int rw)
-{
- struct throtl_service_queue *sq = &tg->service_queue;
- bool limit = tg->bps[rw][LIMIT_LOW] || tg->iops[rw][LIMIT_LOW];
-
- /*
- * if low limit is zero, low limit is always reached.
- * if low limit is non-zero, we can check if there is any request
- * is queued to determine if low limit is reached as we throttle
- * request according to limit.
- */
- return !limit || sq->nr_queued[rw];
-}
-
-static bool throtl_tg_can_upgrade(struct throtl_grp *tg)
-{
- /*
- * cgroup reaches low limit when low limit of READ and WRITE are
- * both reached, it's ok to upgrade to next limit if cgroup reaches
- * low limit
- */
- if (throtl_low_limit_reached(tg, READ) &&
- throtl_low_limit_reached(tg, WRITE))
- return true;
-
- if (time_after_eq(jiffies,
- tg_last_low_overflow_time(tg) + tg->td->throtl_slice) &&
- throtl_tg_is_idle(tg))
- return true;
- return false;
-}
-
-static bool throtl_hierarchy_can_upgrade(struct throtl_grp *tg)
-{
- while (true) {
- if (throtl_tg_can_upgrade(tg))
- return true;
- tg = sq_to_tg(tg->service_queue.parent_sq);
- if (!tg || !tg_to_blkg(tg)->parent)
- return false;
- }
- return false;
-}
-
-static bool throtl_can_upgrade(struct throtl_data *td,
- struct throtl_grp *this_tg)
-{
- struct cgroup_subsys_state *pos_css;
- struct blkcg_gq *blkg;
-
- if (td->limit_index != LIMIT_LOW)
- return false;
-
- if (time_before(jiffies, td->low_downgrade_time + td->throtl_slice))
- return false;
-
- rcu_read_lock();
- blkg_for_each_descendant_post(blkg, pos_css, td->queue->root_blkg) {
- struct throtl_grp *tg = blkg_to_tg(blkg);
-
- if (tg == this_tg)
- continue;
- if (!list_empty(&tg_to_blkg(tg)->blkcg->css.children))
- continue;
- if (!throtl_hierarchy_can_upgrade(tg)) {
- rcu_read_unlock();
- return false;
- }
- }
- rcu_read_unlock();
- return true;
-}
-
-static void throtl_upgrade_check(struct throtl_grp *tg)
-{
- unsigned long now = jiffies;
-
- if (tg->td->limit_index != LIMIT_LOW)
- return;
-
- if (time_after(tg->last_check_time + tg->td->throtl_slice, now))
- return;
-
- tg->last_check_time = now;
-
- if (!time_after_eq(now,
- __tg_last_low_overflow_time(tg) + tg->td->throtl_slice))
- return;
-
- if (throtl_can_upgrade(tg->td, NULL))
- throtl_upgrade_state(tg->td);
-}
-
-static void throtl_upgrade_state(struct throtl_data *td)
-{
- struct cgroup_subsys_state *pos_css;
- struct blkcg_gq *blkg;
-
- throtl_log(&td->service_queue, "upgrade to max");
- td->limit_index = LIMIT_MAX;
- td->low_upgrade_time = jiffies;
- td->scale = 0;
- rcu_read_lock();
- blkg_for_each_descendant_post(blkg, pos_css, td->queue->root_blkg) {
- struct throtl_grp *tg = blkg_to_tg(blkg);
- struct throtl_service_queue *sq = &tg->service_queue;
-
- tg->disptime = jiffies - 1;
- throtl_select_dispatch(sq);
- throtl_schedule_next_dispatch(sq, true);
- }
- rcu_read_unlock();
- throtl_select_dispatch(&td->service_queue);
- throtl_schedule_next_dispatch(&td->service_queue, true);
- queue_work(kthrotld_workqueue, &td->dispatch_work);
-}
-
-static void throtl_downgrade_state(struct throtl_data *td)
-{
- td->scale /= 2;
-
- throtl_log(&td->service_queue, "downgrade, scale %d", td->scale);
- if (td->scale) {
- td->low_upgrade_time = jiffies - td->scale * td->throtl_slice;
- return;
- }
-
- td->limit_index = LIMIT_LOW;
- td->low_downgrade_time = jiffies;
-}
-
-static bool throtl_tg_can_downgrade(struct throtl_grp *tg)
-{
- struct throtl_data *td = tg->td;
- unsigned long now = jiffies;
-
- /*
- * If cgroup is below low limit, consider downgrade and throttle other
- * cgroups
- */
- if (time_after_eq(now, tg_last_low_overflow_time(tg) +
- td->throtl_slice) &&
- (!throtl_tg_is_idle(tg) ||
- !list_empty(&tg_to_blkg(tg)->blkcg->css.children)))
- return true;
- return false;
-}
-
-static bool throtl_hierarchy_can_downgrade(struct throtl_grp *tg)
-{
- struct throtl_data *td = tg->td;
-
- if (time_before(jiffies, td->low_upgrade_time + td->throtl_slice))
- return false;
-
- while (true) {
- if (!throtl_tg_can_downgrade(tg))
- return false;
- tg = sq_to_tg(tg->service_queue.parent_sq);
- if (!tg || !tg_to_blkg(tg)->parent)
- break;
- }
- return true;
-}
-
-static void throtl_downgrade_check(struct throtl_grp *tg)
-{
- uint64_t bps;
- unsigned int iops;
- unsigned long elapsed_time;
- unsigned long now = jiffies;
-
- if (tg->td->limit_index != LIMIT_MAX ||
- !tg->td->limit_valid[LIMIT_LOW])
- return;
- if (!list_empty(&tg_to_blkg(tg)->blkcg->css.children))
- return;
- if (time_after(tg->last_check_time + tg->td->throtl_slice, now))
- return;
-
- elapsed_time = now - tg->last_check_time;
- tg->last_check_time = now;
-
- if (time_before(now, tg_last_low_overflow_time(tg) +
- tg->td->throtl_slice))
- return;
-
- if (tg->bps[READ][LIMIT_LOW]) {
- bps = tg->last_bytes_disp[READ] * HZ;
- do_div(bps, elapsed_time);
- if (bps >= tg->bps[READ][LIMIT_LOW])
- tg->last_low_overflow_time[READ] = now;
- }
-
- if (tg->bps[WRITE][LIMIT_LOW]) {
- bps = tg->last_bytes_disp[WRITE] * HZ;
- do_div(bps, elapsed_time);
- if (bps >= tg->bps[WRITE][LIMIT_LOW])
- tg->last_low_overflow_time[WRITE] = now;
- }
-
- if (tg->iops[READ][LIMIT_LOW]) {
- iops = tg->last_io_disp[READ] * HZ / elapsed_time;
- if (iops >= tg->iops[READ][LIMIT_LOW])
- tg->last_low_overflow_time[READ] = now;
- }
-
- if (tg->iops[WRITE][LIMIT_LOW]) {
- iops = tg->last_io_disp[WRITE] * HZ / elapsed_time;
- if (iops >= tg->iops[WRITE][LIMIT_LOW])
- tg->last_low_overflow_time[WRITE] = now;
- }
-
- /*
- * If cgroup is below low limit, consider downgrade and throttle other
- * cgroups
- */
- if (throtl_hierarchy_can_downgrade(tg))
- throtl_downgrade_state(tg->td);
-
- tg->last_bytes_disp[READ] = 0;
- tg->last_bytes_disp[WRITE] = 0;
- tg->last_io_disp[READ] = 0;
- tg->last_io_disp[WRITE] = 0;
-}
-
-static void blk_throtl_update_idletime(struct throtl_grp *tg)
-{
- unsigned long now;
- unsigned long last_finish_time = tg->last_finish_time;
-
- if (last_finish_time == 0)
- return;
-
- now = blk_time_get_ns() >> 10;
- if (now <= last_finish_time ||
- last_finish_time == tg->checked_last_finish_time)
- return;
-
- tg->avg_idletime = (tg->avg_idletime * 7 + now - last_finish_time) >> 3;
- tg->checked_last_finish_time = last_finish_time;
-}
-
-static void throtl_update_latency_buckets(struct throtl_data *td)
-{
- struct avg_latency_bucket avg_latency[2][LATENCY_BUCKET_SIZE];
- int i, cpu, rw;
- unsigned long last_latency[2] = { 0 };
- unsigned long latency[2];
-
- if (!blk_queue_nonrot(td->queue) || !td->limit_valid[LIMIT_LOW])
- return;
- if (time_before(jiffies, td->last_calculate_time + HZ))
- return;
- td->last_calculate_time = jiffies;
-
- memset(avg_latency, 0, sizeof(avg_latency));
- for (rw = READ; rw <= WRITE; rw++) {
- for (i = 0; i < LATENCY_BUCKET_SIZE; i++) {
- struct latency_bucket *tmp = &td->tmp_buckets[rw][i];
-
- for_each_possible_cpu(cpu) {
- struct latency_bucket *bucket;
-
- /* this isn't race free, but ok in practice */
- bucket = per_cpu_ptr(td->latency_buckets[rw],
- cpu);
- tmp->total_latency += bucket[i].total_latency;
- tmp->samples += bucket[i].samples;
- bucket[i].total_latency = 0;
- bucket[i].samples = 0;
- }
-
- if (tmp->samples >= 32) {
- int samples = tmp->samples;
-
- latency[rw] = tmp->total_latency;
-
- tmp->total_latency = 0;
- tmp->samples = 0;
- latency[rw] /= samples;
- if (latency[rw] == 0)
- continue;
- avg_latency[rw][i].latency = latency[rw];
- }
- }
- }
-
- for (rw = READ; rw <= WRITE; rw++) {
- for (i = 0; i < LATENCY_BUCKET_SIZE; i++) {
- if (!avg_latency[rw][i].latency) {
- if (td->avg_buckets[rw][i].latency < last_latency[rw])
- td->avg_buckets[rw][i].latency =
- last_latency[rw];
- continue;
- }
-
- if (!td->avg_buckets[rw][i].valid)
- latency[rw] = avg_latency[rw][i].latency;
- else
- latency[rw] = (td->avg_buckets[rw][i].latency * 7 +
- avg_latency[rw][i].latency) >> 3;
-
- td->avg_buckets[rw][i].latency = max(latency[rw],
- last_latency[rw]);
- td->avg_buckets[rw][i].valid = true;
- last_latency[rw] = td->avg_buckets[rw][i].latency;
- }
- }
-
- for (i = 0; i < LATENCY_BUCKET_SIZE; i++)
- throtl_log(&td->service_queue,
- "Latency bucket %d: read latency=%ld, read valid=%d, "
- "write latency=%ld, write valid=%d", i,
- td->avg_buckets[READ][i].latency,
- td->avg_buckets[READ][i].valid,
- td->avg_buckets[WRITE][i].latency,
- td->avg_buckets[WRITE][i].valid);
-}
-#else
-static inline void throtl_update_latency_buckets(struct throtl_data *td)
-{
-}
-
-static void blk_throtl_update_idletime(struct throtl_grp *tg)
-{
-}
-
-static void throtl_downgrade_check(struct throtl_grp *tg)
-{
-}
-
-static void throtl_upgrade_check(struct throtl_grp *tg)
-{
-}
-
-static bool throtl_can_upgrade(struct throtl_data *td,
- struct throtl_grp *this_tg)
-{
- return false;
-}
-
-static void throtl_upgrade_state(struct throtl_data *td)
-{
-}
-#endif
-
bool __blk_throtl_bio(struct bio *bio)
{
struct request_queue *q = bdev_get_queue(bio->bi_bdev);
struct throtl_data *td = tg->td;
rcu_read_lock();
-
spin_lock_irq(&q->queue_lock);
-
- throtl_update_latency_buckets(td);
-
- blk_throtl_update_idletime(tg);
-
sq = &tg->service_queue;
-again:
while (true) {
if (tg->last_low_overflow_time[rw] == 0)
tg->last_low_overflow_time[rw] = jiffies;
- throtl_downgrade_check(tg);
- throtl_upgrade_check(tg);
/* throtl is FIFO - if bios are already queued, should queue */
if (sq->nr_queued[rw])
break;
/* if above limits, break to queue */
if (!tg_may_dispatch(tg, bio, NULL)) {
tg->last_low_overflow_time[rw] = jiffies;
- if (throtl_can_upgrade(td, tg)) {
- throtl_upgrade_state(td);
- goto again;
- }
break;
}
}
out_unlock:
-#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
- if (throttled || !td->track_bio_latency)
- bio->bi_issue.value |= BIO_ISSUE_THROTL_SKIP_LATENCY;
-#endif
spin_unlock_irq(&q->queue_lock);
rcu_read_unlock();
return throttled;
}
-#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
-static void throtl_track_latency(struct throtl_data *td, sector_t size,
- enum req_op op, unsigned long time)
-{
- const bool rw = op_is_write(op);
- struct latency_bucket *latency;
- int index;
-
- if (!td || td->limit_index != LIMIT_LOW ||
- !(op == REQ_OP_READ || op == REQ_OP_WRITE) ||
- !blk_queue_nonrot(td->queue))
- return;
-
- index = request_bucket_index(size);
-
- latency = get_cpu_ptr(td->latency_buckets[rw]);
- latency[index].total_latency += time;
- latency[index].samples++;
- put_cpu_ptr(td->latency_buckets[rw]);
-}
-
-void blk_throtl_stat_add(struct request *rq, u64 time_ns)
-{
- struct request_queue *q = rq->q;
- struct throtl_data *td = q->td;
-
- throtl_track_latency(td, blk_rq_stats_sectors(rq), req_op(rq),
- time_ns >> 10);
-}
-
-void blk_throtl_bio_endio(struct bio *bio)
-{
- struct blkcg_gq *blkg;
- struct throtl_grp *tg;
- u64 finish_time_ns;
- unsigned long finish_time;
- unsigned long start_time;
- unsigned long lat;
- int rw = bio_data_dir(bio);
-
- blkg = bio->bi_blkg;
- if (!blkg)
- return;
- tg = blkg_to_tg(blkg);
- if (!tg->td->limit_valid[LIMIT_LOW])
- return;
-
- finish_time_ns = blk_time_get_ns();
- tg->last_finish_time = finish_time_ns >> 10;
-
- start_time = bio_issue_time(&bio->bi_issue) >> 10;
- finish_time = __bio_issue_time(finish_time_ns) >> 10;
- if (!start_time || finish_time <= start_time)
- return;
-
- lat = finish_time - start_time;
- /* this is only for bio based driver */
- if (!(bio->bi_issue.value & BIO_ISSUE_THROTL_SKIP_LATENCY))
- throtl_track_latency(tg->td, bio_issue_size(&bio->bi_issue),
- bio_op(bio), lat);
-
- if (tg->latency_target && lat >= tg->td->filtered_latency) {
- int bucket;
- unsigned int threshold;
-
- bucket = request_bucket_index(bio_issue_size(&bio->bi_issue));
- threshold = tg->td->avg_buckets[rw][bucket].latency +
- tg->latency_target;
- if (lat > threshold)
- tg->bad_bio_cnt++;
- /*
- * Not race free, could get wrong count, which means cgroups
- * will be throttled
- */
- tg->bio_cnt++;
- }
-
- if (time_after(jiffies, tg->bio_cnt_reset_time) || tg->bio_cnt > 1024) {
- tg->bio_cnt_reset_time = tg->td->throtl_slice + jiffies;
- tg->bio_cnt /= 2;
- tg->bad_bio_cnt /= 2;
- }
-}
-#endif
-
-int blk_throtl_init(struct gendisk *disk)
-{
- struct request_queue *q = disk->queue;
- struct throtl_data *td;
- int ret;
-
- td = kzalloc_node(sizeof(*td), GFP_KERNEL, q->node);
- if (!td)
- return -ENOMEM;
- td->latency_buckets[READ] = __alloc_percpu(sizeof(struct latency_bucket) *
- LATENCY_BUCKET_SIZE, __alignof__(u64));
- if (!td->latency_buckets[READ]) {
- kfree(td);
- return -ENOMEM;
- }
- td->latency_buckets[WRITE] = __alloc_percpu(sizeof(struct latency_bucket) *
- LATENCY_BUCKET_SIZE, __alignof__(u64));
- if (!td->latency_buckets[WRITE]) {
- free_percpu(td->latency_buckets[READ]);
- kfree(td);
- return -ENOMEM;
- }
-
- INIT_WORK(&td->dispatch_work, blk_throtl_dispatch_work_fn);
- throtl_service_queue_init(&td->service_queue);
-
- q->td = td;
- td->queue = q;
-
- td->limit_valid[LIMIT_MAX] = true;
- td->limit_index = LIMIT_MAX;
- td->low_upgrade_time = jiffies;
- td->low_downgrade_time = jiffies;
-
- /* activate policy */
- ret = blkcg_activate_policy(disk, &blkcg_policy_throtl);
- if (ret) {
- free_percpu(td->latency_buckets[READ]);
- free_percpu(td->latency_buckets[WRITE]);
- kfree(td);
- }
- return ret;
-}
-
void blk_throtl_exit(struct gendisk *disk)
{
struct request_queue *q = disk->queue;
- BUG_ON(!q->td);
+ if (!blk_throtl_activated(q))
+ return;
+
del_timer_sync(&q->td->service_queue.pending_timer);
throtl_shutdown_wq(q);
blkcg_deactivate_policy(disk, &blkcg_policy_throtl);
- free_percpu(q->td->latency_buckets[READ]);
- free_percpu(q->td->latency_buckets[WRITE]);
kfree(q->td);
}
-void blk_throtl_register(struct gendisk *disk)
-{
- struct request_queue *q = disk->queue;
- struct throtl_data *td;
- int i;
-
- td = q->td;
- BUG_ON(!td);
-
- if (blk_queue_nonrot(q)) {
- td->throtl_slice = DFL_THROTL_SLICE_SSD;
- td->filtered_latency = LATENCY_FILTERED_SSD;
- } else {
- td->throtl_slice = DFL_THROTL_SLICE_HD;
- td->filtered_latency = LATENCY_FILTERED_HD;
- for (i = 0; i < LATENCY_BUCKET_SIZE; i++) {
- td->avg_buckets[READ][i].latency = DFL_HD_BASELINE_LATENCY;
- td->avg_buckets[WRITE][i].latency = DFL_HD_BASELINE_LATENCY;
- }
- }
-#ifndef CONFIG_BLK_DEV_THROTTLING_LOW
- /* if no low limit, use previous default */
- td->throtl_slice = DFL_THROTL_SLICE_HD;
-
-#else
- td->track_bio_latency = !queue_is_mq(q);
- if (!td->track_bio_latency)
- blk_stat_enable_accounting(q);
-#endif
-}
-
-#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
-ssize_t blk_throtl_sample_time_show(struct request_queue *q, char *page)
-{
- if (!q->td)
- return -EINVAL;
- return sprintf(page, "%u\n", jiffies_to_msecs(q->td->throtl_slice));
-}
-
-ssize_t blk_throtl_sample_time_store(struct request_queue *q,
- const char *page, size_t count)
-{
- unsigned long v;
- unsigned long t;
-
- if (!q->td)
- return -EINVAL;
- if (kstrtoul(page, 10, &v))
- return -EINVAL;
- t = msecs_to_jiffies(v);
- if (t == 0 || t > MAX_THROTL_SLICE)
- return -EINVAL;
- q->td->throtl_slice = t;
- return count;
-}
-#endif
-
static int __init throtl_init(void)
{
kthrotld_workqueue = alloc_workqueue("kthrotld", WQ_MEM_RECLAIM, 0);
projects / linux-2.6-microblaze.git / blobdiff