* [PATCH 2/4] blkio: blkio cgroup interface related changes to support new throttling policy
2010-09-07 20:53 [RFC PATCH] Block device bio throttling support [V2] Vivek Goyal
2010-09-07 20:53 ` [PATCH 1/4] Kill the header printed at the start of blkio.weight_device file Vivek Goyal
@ 2010-09-07 20:53 ` Vivek Goyal
2010-09-07 20:53 ` [PATCH 3/4] block: Core throttling logic implementation Vivek Goyal
2010-09-07 20:53 ` [PATCH 4/4] blkio: Documentation update Vivek Goyal
3 siblings, 0 replies; 5+ messages in thread
From: Vivek Goyal @ 2010-09-07 20:53 UTC (permalink / raw)
To: linux-kernel, axboe; +Cc: nauman, dpshah, guijianfeng, vgoyal
o Changes to blkio controller cgroup interface to accomodate more than one
policy. New policy being introduced is throttling.
Signed-off-by: Vivek Goyal <vgoyal@redhat.com>
---
block/blk-cgroup.c | 697 ++++++++++++++++++++++++++++++++++++++++------------
block/blk-cgroup.h | 75 ++++++-
block/cfq.h | 2 +-
3 files changed, 618 insertions(+), 156 deletions(-)
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index c1a39d9..004aeb3 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -37,6 +37,12 @@ static void blkiocg_attach(struct cgroup_subsys *, struct cgroup *,
static void blkiocg_destroy(struct cgroup_subsys *, struct cgroup *);
static int blkiocg_populate(struct cgroup_subsys *, struct cgroup *);
+/* for encoding cft->private value on file */
+#define BLKIOFILE_PRIVATE(x, val) (((x) << 16) | (val))
+/* What policy owns the file, proportional or throttle */
+#define BLKIOFILE_POLICY(val) (((val) >> 16) & 0xffff)
+#define BLKIOFILE_ATTR(val) ((val) & 0xffff)
+
struct cgroup_subsys blkio_subsys = {
.name = "blkio",
.create = blkiocg_create,
@@ -65,14 +71,55 @@ static inline void blkio_policy_delete_node(struct blkio_policy_node *pn)
list_del(&pn->node);
}
+static inline bool cftype_blkg_same_policy(struct cftype *cft,
+ struct blkio_group *blkg)
+{
+ enum blkio_policy_id plid = BLKIOFILE_POLICY(cft->private);
+
+ if (blkg->plid == plid)
+ return 1;
+
+ return 0;
+}
+
+/* Determines if policy node matches cgroup file being accessed */
+static inline bool pn_matches_cftype(struct cftype *cft,
+ struct blkio_policy_node *pn)
+{
+ enum blkio_policy_id plid = BLKIOFILE_POLICY(cft->private);
+ int name = BLKIOFILE_ATTR(cft->private);
+
+ if (plid != pn->plid)
+ return 0;
+
+ if (plid == BLKIO_POLICY_PROP) {
+ switch(name) {
+ case BLKIO_PROP_weight_device:
+ return (pn->rulet == BLKIO_RULE_WEIGHT);
+ }
+ }
+
+ if (plid == BLKIO_POLICY_THROTL) {
+ switch(name) {
+ case BLKIO_THROTL_read_bps_device:
+ return (pn->rulet == BLKIO_RULE_READ);
+ case BLKIO_THROTL_write_bps_device:
+ return (pn->rulet == BLKIO_RULE_WRITE);
+ }
+ }
+
+ return 0;
+}
+
/* Must be called with blkcg->lock held */
static struct blkio_policy_node *
-blkio_policy_search_node(const struct blkio_cgroup *blkcg, dev_t dev)
+blkio_policy_search_node(const struct blkio_cgroup *blkcg, dev_t dev,
+ enum blkio_policy_id plid, enum blkio_rule_type rulet)
{
struct blkio_policy_node *pn;
list_for_each_entry(pn, &blkcg->policy_list, node) {
- if (pn->dev == dev)
+ if (pn->dev == dev && pn->plid == plid && pn->rulet == rulet)
return pn;
}
@@ -86,6 +133,33 @@ struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup)
}
EXPORT_SYMBOL_GPL(cgroup_to_blkio_cgroup);
+static inline void
+blkio_update_group_weight(struct blkio_group *blkg, unsigned int weight)
+{
+ struct blkio_policy_type *blkiop;
+
+ list_for_each_entry(blkiop, &blkio_list, list) {
+ if (blkiop->ops.blkio_update_group_weight_fn)
+ blkiop->ops.blkio_update_group_weight_fn(blkg, weight);
+ }
+}
+
+static inline void blkio_update_group_bps(struct blkio_group *blkg, u64 bps,
+ enum blkio_rule_type rulet)
+{
+ struct blkio_policy_type *blkiop;
+
+ list_for_each_entry(blkiop, &blkio_list, list) {
+ if (rulet == BLKIO_RULE_READ
+ && blkiop->ops.blkio_update_group_read_bps_fn)
+ blkiop->ops.blkio_update_group_read_bps_fn(blkg, bps);
+
+ if (rulet == BLKIO_RULE_WRITE
+ && blkiop->ops.blkio_update_group_write_bps_fn)
+ blkiop->ops.blkio_update_group_write_bps_fn(blkg, bps);
+ }
+}
+
/*
* Add to the appropriate stat variable depending on the request type.
* This should be called with the blkg->stats_lock held.
@@ -341,7 +415,8 @@ void blkiocg_update_io_merged_stats(struct blkio_group *blkg, bool direction,
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)
+ struct blkio_group *blkg, void *key, dev_t dev,
+ enum blkio_policy_id plid)
{
unsigned long flags;
@@ -350,6 +425,7 @@ void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
rcu_assign_pointer(blkg->key, key);
blkg->blkcg_id = css_id(&blkcg->css);
hlist_add_head_rcu(&blkg->blkcg_node, &blkcg->blkg_list);
+ blkg->plid = plid;
spin_unlock_irqrestore(&blkcg->lock, flags);
/* Need to take css reference ? */
cgroup_path(blkcg->css.cgroup, blkg->path, sizeof(blkg->path));
@@ -408,51 +484,6 @@ struct blkio_group *blkiocg_lookup_group(struct blkio_cgroup *blkcg, void *key)
}
EXPORT_SYMBOL_GPL(blkiocg_lookup_group);
-#define SHOW_FUNCTION(__VAR) \
-static u64 blkiocg_##__VAR##_read(struct cgroup *cgroup, \
- struct cftype *cftype) \
-{ \
- struct blkio_cgroup *blkcg; \
- \
- blkcg = cgroup_to_blkio_cgroup(cgroup); \
- return (u64)blkcg->__VAR; \
-}
-
-SHOW_FUNCTION(weight);
-#undef SHOW_FUNCTION
-
-static int
-blkiocg_weight_write(struct cgroup *cgroup, struct cftype *cftype, u64 val)
-{
- struct blkio_cgroup *blkcg;
- 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;
-
- blkcg = cgroup_to_blkio_cgroup(cgroup);
- 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);
- }
- spin_unlock_irq(&blkcg->lock);
- spin_unlock(&blkio_list_lock);
- return 0;
-}
-
static int
blkiocg_reset_stats(struct cgroup *cgroup, struct cftype *cftype, u64 val)
{
@@ -593,52 +624,6 @@ static uint64_t blkio_get_stat(struct blkio_group *blkg,
return disk_total;
}
-#define SHOW_FUNCTION_PER_GROUP(__VAR, type, show_total) \
-static int blkiocg_##__VAR##_read(struct cgroup *cgroup, \
- 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; \
- \
- blkcg = cgroup_to_blkio_cgroup(cgroup); \
- rcu_read_lock(); \
- hlist_for_each_entry_rcu(blkg, n, &blkcg->blkg_list, blkcg_node) {\
- 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, 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, 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
-
static int blkio_check_dev_num(dev_t dev)
{
int part = 0;
@@ -652,11 +637,13 @@ static int blkio_check_dev_num(dev_t dev)
}
static int blkio_policy_parse_and_set(char *buf,
- struct blkio_policy_node *newpn)
+ struct blkio_policy_node *newpn, enum blkio_policy_id plid,
+ enum blkio_rule_type rulet)
{
char *s[4], *p, *major_s = NULL, *minor_s = NULL;
int ret;
unsigned long major, minor, temp;
+ u64 bps;
int i = 0;
dev_t dev;
@@ -705,12 +692,26 @@ static int blkio_policy_parse_and_set(char *buf,
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;
+ switch (plid) {
+ case BLKIO_POLICY_PROP:
+ ret = strict_strtoul(s[1], 10, &temp);
+ if (ret || (temp < BLKIO_WEIGHT_MIN && temp > 0) ||
+ temp > BLKIO_WEIGHT_MAX)
+ return -EINVAL;
- newpn->weight = temp;
+ newpn->plid = plid;
+ newpn->rulet = rulet;
+ newpn->val.weight = temp;
+ break;
+ case BLKIO_POLICY_THROTL:
+ ret = strict_strtoull(s[1], 10, &bps);
+ if (ret)
+ return -EINVAL;
+
+ newpn->plid = plid;
+ newpn->rulet = rulet;
+ newpn->val.bps = bps;
+ }
return 0;
}
@@ -720,26 +721,121 @@ unsigned int blkcg_get_weight(struct blkio_cgroup *blkcg,
{
struct blkio_policy_node *pn;
- pn = blkio_policy_search_node(blkcg, dev);
+ pn = blkio_policy_search_node(blkcg, dev, BLKIO_POLICY_PROP,
+ BLKIO_RULE_WEIGHT);
if (pn)
- return pn->weight;
+ return pn->val.weight;
else
return blkcg->weight;
}
EXPORT_SYMBOL_GPL(blkcg_get_weight);
+uint64_t blkcg_get_read_bps(struct blkio_cgroup *blkcg, dev_t dev)
+{
+ struct blkio_policy_node *pn;
+
+ pn = blkio_policy_search_node(blkcg, dev, BLKIO_POLICY_THROTL,
+ BLKIO_RULE_READ);
+ if (pn)
+ return pn->val.bps;
+ else
+ return -1;
+}
+EXPORT_SYMBOL_GPL(blkcg_get_read_bps);
-static int blkiocg_weight_device_write(struct cgroup *cgrp, struct cftype *cft,
- const char *buffer)
+uint64_t blkcg_get_write_bps(struct blkio_cgroup *blkcg, dev_t dev)
+{
+ struct blkio_policy_node *pn;
+ pn = blkio_policy_search_node(blkcg, dev, BLKIO_POLICY_THROTL,
+ BLKIO_RULE_WRITE);
+ if (pn)
+ return pn->val.bps;
+ else
+ return -1;
+}
+EXPORT_SYMBOL_GPL(blkcg_get_write_bps);
+
+/* Checks whether user asked for deleting a policy rule */
+static bool blkio_delete_rule_command(struct blkio_policy_node *pn)
+{
+ switch(pn->plid) {
+ case BLKIO_POLICY_PROP:
+ if (pn->val.weight == 0)
+ return 1;
+ break;
+ case BLKIO_POLICY_THROTL:
+ if (pn->val.bps == 0)
+ return 1;
+ break;
+ default:
+ BUG();
+ }
+
+ return 0;
+}
+
+static void blkio_update_policy_rule(struct blkio_policy_node *oldpn,
+ struct blkio_policy_node *newpn)
+{
+ switch(oldpn->plid) {
+ case BLKIO_POLICY_PROP:
+ oldpn->val.weight = newpn->val.weight;
+ break;
+ case BLKIO_POLICY_THROTL:
+ oldpn->val.bps = newpn->val.bps;
+ break;
+ default:
+ BUG();
+ }
+}
+
+/*
+ * A policy node rule has been updated. Propogate this update to all the
+ * block groups which might be affected by this update.
+ */
+static void blkio_update_policy_node_blkg(struct blkio_cgroup *blkcg,
+ struct blkio_policy_node *pn)
+{
+ struct blkio_group *blkg;
+ struct hlist_node *n;
+ enum blkio_rule_type rulet = pn->rulet;
+ unsigned int weight;
+ u64 bps;
+
+ spin_lock(&blkio_list_lock);
+ spin_lock_irq(&blkcg->lock);
+
+ hlist_for_each_entry(blkg, n, &blkcg->blkg_list, blkcg_node) {
+ if (pn->dev == blkg->dev) {
+ if (pn->plid == BLKIO_POLICY_PROP) {
+ weight = pn->val.weight ? pn->val.weight :
+ blkcg->weight;
+ blkio_update_group_weight(blkg, weight);
+ } else {
+
+ bps = pn->val.bps ? pn->val.bps : (-1);
+ blkio_update_group_bps(blkg, bps, rulet);
+ }
+ }
+ }
+
+ spin_unlock_irq(&blkcg->lock);
+ spin_unlock(&blkio_list_lock);
+
+}
+
+
+static int blkiocg_file_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;
+ enum blkio_policy_id plid = BLKIOFILE_POLICY(cft->private);
+ int name = BLKIOFILE_ATTR(cft->private);
+ enum blkio_rule_type rulet;
buf = kstrdup(buffer, GFP_KERNEL);
if (!buf)
@@ -751,7 +847,30 @@ static int blkiocg_weight_device_write(struct cgroup *cgrp, struct cftype *cft,
goto free_buf;
}
- ret = blkio_policy_parse_and_set(buf, newpn);
+ switch (plid) {
+ case BLKIO_POLICY_PROP:
+ if (name == BLKIO_PROP_weight_device) {
+ rulet = BLKIO_RULE_WEIGHT;
+ ret = blkio_policy_parse_and_set(buf, newpn, plid, 0);
+ } else
+ BUG();
+ break;
+ case BLKIO_POLICY_THROTL:
+ if (name == BLKIO_THROTL_read_bps_device) {
+ rulet = BLKIO_RULE_READ;
+ ret = blkio_policy_parse_and_set(buf, newpn, plid,
+ rulet);
+ } else if (name == BLKIO_THROTL_write_bps_device) {
+ rulet = BLKIO_RULE_WRITE;
+ ret = blkio_policy_parse_and_set(buf, newpn, plid,
+ rulet);
+ } else
+ BUG();
+ break;
+ default:
+ BUG();
+ }
+
if (ret)
goto free_newpn;
@@ -759,9 +878,9 @@ static int blkiocg_weight_device_write(struct cgroup *cgrp, struct cftype *cft,
spin_lock_irq(&blkcg->lock);
- pn = blkio_policy_search_node(blkcg, newpn->dev);
+ pn = blkio_policy_search_node(blkcg, newpn->dev, plid, rulet);
if (!pn) {
- if (newpn->weight != 0) {
+ if (!blkio_delete_rule_command(newpn)) {
blkio_policy_insert_node(blkcg, newpn);
keep_newpn = 1;
}
@@ -769,33 +888,17 @@ static int blkiocg_weight_device_write(struct cgroup *cgrp, struct cftype *cft,
goto update_io_group;
}
- if (newpn->weight == 0) {
- /* weight == 0 means deleteing a specific weight */
+ if (blkio_delete_rule_command(newpn)) {
blkio_policy_delete_node(pn);
spin_unlock_irq(&blkcg->lock);
goto update_io_group;
}
spin_unlock_irq(&blkcg->lock);
- pn->weight = newpn->weight;
+ blkio_update_policy_rule(pn, newpn);
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);
+ blkio_update_policy_node_blkg(blkcg, newpn);
free_newpn:
if (!keep_newpn)
@@ -805,21 +908,251 @@ free_buf:
return ret;
}
-static int blkiocg_weight_device_read(struct cgroup *cgrp, struct cftype *cft,
- struct seq_file *m)
+static void
+blkio_print_policy_node(struct seq_file *m, struct blkio_policy_node *pn)
+{
+ switch(pn->plid) {
+ case BLKIO_POLICY_PROP:
+ if (pn->rulet == BLKIO_RULE_WEIGHT)
+ seq_printf(m, "%u:%u\t%u\n", MAJOR(pn->dev),
+ MINOR(pn->dev), pn->val.weight);
+ break;
+ case BLKIO_POLICY_THROTL:
+ if (pn->rulet == BLKIO_RULE_READ)
+ seq_printf(m, "%u:%u\t%llu\n", MAJOR(pn->dev),
+ MINOR(pn->dev), pn->val.bps);
+ else if (pn->rulet == BLKIO_RULE_WRITE)
+ seq_printf(m, "%u:%u\t%llu\n", MAJOR(pn->dev),
+ MINOR(pn->dev), pn->val.bps);
+ else
+ BUG();
+ break;
+ default:
+ BUG();
+ }
+}
+
+/* cgroup files which read their data from policy nodes end up here */
+static void blkio_read_policy_node_files(struct cftype *cft,
+ struct blkio_cgroup *blkcg, struct seq_file *m)
{
- struct blkio_cgroup *blkcg;
struct blkio_policy_node *pn;
- blkcg = cgroup_to_blkio_cgroup(cgrp);
if (!list_empty(&blkcg->policy_list)) {
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);
+ if (!pn_matches_cftype(cft, pn))
+ continue;
+ blkio_print_policy_node(m, pn);
}
spin_unlock_irq(&blkcg->lock);
}
+}
+
+static int blkiocg_file_read(struct cgroup *cgrp, struct cftype *cft,
+ struct seq_file *m)
+{
+ struct blkio_cgroup *blkcg;
+ enum blkio_policy_id plid = BLKIOFILE_POLICY(cft->private);
+ int name = BLKIOFILE_ATTR(cft->private);
+
+ blkcg = cgroup_to_blkio_cgroup(cgrp);
+
+ switch(plid) {
+ case BLKIO_POLICY_PROP:
+ switch(name) {
+ case BLKIO_PROP_weight_device:
+ blkio_read_policy_node_files(cft, blkcg, m);
+ return 0;
+ default:
+ BUG();
+ }
+ break;
+ case BLKIO_POLICY_THROTL:
+ switch(name){
+ case BLKIO_THROTL_read_bps_device:
+ case BLKIO_THROTL_write_bps_device:
+ blkio_read_policy_node_files(cft, blkcg, m);
+ return 0;
+ default:
+ BUG();
+ }
+ break;
+ default:
+ BUG();
+ }
+
+ return 0;
+}
+
+static int blkio_read_blkg_stats(struct blkio_cgroup *blkcg,
+ struct cftype *cft, struct cgroup_map_cb *cb, enum stat_type type,
+ bool show_total)
+{
+ struct blkio_group *blkg;
+ struct hlist_node *n;
+ uint64_t cgroup_total = 0;
+
+ rcu_read_lock();
+ hlist_for_each_entry_rcu(blkg, n, &blkcg->blkg_list, blkcg_node) {
+ if (blkg->dev) {
+ if (!cftype_blkg_same_policy(cft, blkg))
+ continue;
+ 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();
+ return 0;
+}
+
+/* All map kind of cgroup file get serviced by this function */
+static int blkiocg_file_read_map(struct cgroup *cgrp, struct cftype *cft,
+ struct cgroup_map_cb *cb)
+{
+ struct blkio_cgroup *blkcg;
+ enum blkio_policy_id plid = BLKIOFILE_POLICY(cft->private);
+ int name = BLKIOFILE_ATTR(cft->private);
+
+ blkcg = cgroup_to_blkio_cgroup(cgrp);
+
+ switch(plid) {
+ case BLKIO_POLICY_PROP:
+ switch(name) {
+ case BLKIO_PROP_time:
+ return blkio_read_blkg_stats(blkcg, cft, cb,
+ BLKIO_STAT_TIME, 0);
+ case BLKIO_PROP_sectors:
+ return blkio_read_blkg_stats(blkcg, cft, cb,
+ BLKIO_STAT_SECTORS, 0);
+ case BLKIO_PROP_io_service_bytes:
+ return blkio_read_blkg_stats(blkcg, cft, cb,
+ BLKIO_STAT_SERVICE_BYTES, 1);
+ case BLKIO_PROP_io_serviced:
+ return blkio_read_blkg_stats(blkcg, cft, cb,
+ BLKIO_STAT_SERVICED, 1);
+ case BLKIO_PROP_io_service_time:
+ return blkio_read_blkg_stats(blkcg, cft, cb,
+ BLKIO_STAT_SERVICE_TIME, 1);
+ case BLKIO_PROP_io_wait_time:
+ return blkio_read_blkg_stats(blkcg, cft, cb,
+ BLKIO_STAT_WAIT_TIME, 1);
+ case BLKIO_PROP_io_merged:
+ return blkio_read_blkg_stats(blkcg, cft, cb,
+ BLKIO_STAT_MERGED, 1);
+ case BLKIO_PROP_io_queued:
+ return blkio_read_blkg_stats(blkcg, cft, cb,
+ BLKIO_STAT_QUEUED, 1);
+#ifdef CONFIG_DEBUG_BLK_CGROUP
+ case BLKIO_PROP_dequeue:
+ return blkio_read_blkg_stats(blkcg, cft, cb,
+ BLKIO_STAT_DEQUEUE, 0);
+ case BLKIO_PROP_avg_queue_size:
+ return blkio_read_blkg_stats(blkcg, cft, cb,
+ BLKIO_STAT_AVG_QUEUE_SIZE, 0);
+ case BLKIO_PROP_group_wait_time:
+ return blkio_read_blkg_stats(blkcg, cft, cb,
+ BLKIO_STAT_GROUP_WAIT_TIME, 0);
+ case BLKIO_PROP_idle_time:
+ return blkio_read_blkg_stats(blkcg, cft, cb,
+ BLKIO_STAT_IDLE_TIME, 0);
+ case BLKIO_PROP_empty_time:
+ return blkio_read_blkg_stats(blkcg, cft, cb,
+ BLKIO_STAT_EMPTY_TIME, 0);
+#endif
+ default:
+ BUG();
+ }
+ break;
+
+ case BLKIO_POLICY_THROTL:
+ switch(name){
+ case BLKIO_THROTL_io_service_bytes:
+ return blkio_read_blkg_stats(blkcg, cft, cb,
+ BLKIO_STAT_SERVICE_BYTES, 1);
+ case BLKIO_THROTL_io_serviced:
+ return blkio_read_blkg_stats(blkcg, cft, cb,
+ BLKIO_STAT_SERVICED, 1);
+ default:
+ BUG();
+ }
+ break;
+ default:
+ BUG();
+ }
+
+ return 0;
+}
+
+static int blkio_weight_write(struct blkio_cgroup *blkcg, u64 val)
+{
+ struct blkio_group *blkg;
+ struct hlist_node *n;
+ struct blkio_policy_node *pn;
+
+ if (val < BLKIO_WEIGHT_MIN || val > BLKIO_WEIGHT_MAX)
+ return -EINVAL;
+
+ 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,
+ BLKIO_POLICY_PROP, BLKIO_RULE_WEIGHT);
+ if (pn)
+ continue;
+
+ blkio_update_group_weight(blkg, blkcg->weight);
+ }
+ spin_unlock_irq(&blkcg->lock);
+ spin_unlock(&blkio_list_lock);
+ return 0;
+}
+
+static u64 blkiocg_file_read_u64 (struct cgroup *cgrp, struct cftype *cft) {
+ struct blkio_cgroup *blkcg;
+ enum blkio_policy_id plid = BLKIOFILE_POLICY(cft->private);
+ int name = BLKIOFILE_ATTR(cft->private);
+
+ blkcg = cgroup_to_blkio_cgroup(cgrp);
+
+ switch(plid) {
+ case BLKIO_POLICY_PROP:
+ switch(name) {
+ case BLKIO_PROP_weight:
+ return (u64)blkcg->weight;
+ }
+ break;
+ default:
+ BUG();
+ }
+ return 0;
+}
+
+static int
+blkiocg_file_write_u64(struct cgroup *cgrp, struct cftype *cft, u64 val)
+{
+ struct blkio_cgroup *blkcg;
+ enum blkio_policy_id plid = BLKIOFILE_POLICY(cft->private);
+ int name = BLKIOFILE_ATTR(cft->private);
+
+ blkcg = cgroup_to_blkio_cgroup(cgrp);
+
+ switch(plid) {
+ case BLKIO_POLICY_PROP:
+ switch(name) {
+ case BLKIO_PROP_weight:
+ return blkio_weight_write(blkcg, val);
+ }
+ break;
+ default:
+ BUG();
+ }
return 0;
}
@@ -827,46 +1160,96 @@ static int blkiocg_weight_device_read(struct cgroup *cgrp, struct cftype *cft,
struct cftype blkio_files[] = {
{
.name = "weight_device",
- .read_seq_string = blkiocg_weight_device_read,
- .write_string = blkiocg_weight_device_write,
+ .private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
+ BLKIO_PROP_weight_device),
+ .read_seq_string = blkiocg_file_read,
+ .write_string = blkiocg_file_write,
.max_write_len = 256,
},
{
.name = "weight",
- .read_u64 = blkiocg_weight_read,
- .write_u64 = blkiocg_weight_write,
+ .private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
+ BLKIO_PROP_weight),
+ .read_u64 = blkiocg_file_read_u64,
+ .write_u64 = blkiocg_file_write_u64,
+ },
+
+ {
+ .name = "throttle.read_bps_device",
+ .private = BLKIOFILE_PRIVATE(BLKIO_POLICY_THROTL,
+ BLKIO_THROTL_read_bps_device),
+ .read_seq_string = blkiocg_file_read,
+ .write_string = blkiocg_file_write,
+ .max_write_len = 256,
+ },
+
+ {
+ .name = "throttle.write_bps_device",
+ .private = BLKIOFILE_PRIVATE(BLKIO_POLICY_THROTL,
+ BLKIO_THROTL_write_bps_device),
+ .read_seq_string = blkiocg_file_read,
+ .write_string = blkiocg_file_write,
+ .max_write_len = 256,
},
{
.name = "time",
- .read_map = blkiocg_time_read,
+ .private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
+ BLKIO_PROP_time),
+ .read_map = blkiocg_file_read_map,
},
{
.name = "sectors",
- .read_map = blkiocg_sectors_read,
+ .private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
+ BLKIO_PROP_sectors),
+ .read_map = blkiocg_file_read_map,
},
{
.name = "io_service_bytes",
- .read_map = blkiocg_io_service_bytes_read,
+ .private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
+ BLKIO_PROP_io_service_bytes),
+ .read_map = blkiocg_file_read_map,
+ },
+ {
+ .name = "throttle.io_service_bytes",
+ .private = BLKIOFILE_PRIVATE(BLKIO_POLICY_THROTL,
+ BLKIO_THROTL_io_service_bytes),
+ .read_map = blkiocg_file_read_map,
},
{
.name = "io_serviced",
- .read_map = blkiocg_io_serviced_read,
+ .private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
+ BLKIO_PROP_io_serviced),
+ .read_map = blkiocg_file_read_map,
+ },
+ {
+ .name = "throttle.io_serviced",
+ .private = BLKIOFILE_PRIVATE(BLKIO_POLICY_THROTL,
+ BLKIO_THROTL_io_serviced),
+ .read_map = blkiocg_file_read_map,
},
{
.name = "io_service_time",
- .read_map = blkiocg_io_service_time_read,
+ .private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
+ BLKIO_PROP_io_service_time),
+ .read_map = blkiocg_file_read_map,
},
{
.name = "io_wait_time",
- .read_map = blkiocg_io_wait_time_read,
+ .private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
+ BLKIO_PROP_io_wait_time),
+ .read_map = blkiocg_file_read_map,
},
{
.name = "io_merged",
- .read_map = blkiocg_io_merged_read,
+ .private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
+ BLKIO_PROP_io_merged),
+ .read_map = blkiocg_file_read_map,
},
{
.name = "io_queued",
- .read_map = blkiocg_io_queued_read,
+ .private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
+ BLKIO_PROP_io_queued),
+ .read_map = blkiocg_file_read_map,
},
{
.name = "reset_stats",
@@ -875,23 +1258,33 @@ struct cftype blkio_files[] = {
#ifdef CONFIG_DEBUG_BLK_CGROUP
{
.name = "avg_queue_size",
- .read_map = blkiocg_avg_queue_size_read,
+ .private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
+ BLKIO_PROP_avg_queue_size),
+ .read_map = blkiocg_file_read_map,
},
{
.name = "group_wait_time",
- .read_map = blkiocg_group_wait_time_read,
+ .private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
+ BLKIO_PROP_group_wait_time),
+ .read_map = blkiocg_file_read_map,
},
{
.name = "idle_time",
- .read_map = blkiocg_idle_time_read,
+ .private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
+ BLKIO_PROP_idle_time),
+ .read_map = blkiocg_file_read_map,
},
{
.name = "empty_time",
- .read_map = blkiocg_empty_time_read,
+ .private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
+ BLKIO_PROP_empty_time),
+ .read_map = blkiocg_file_read_map,
},
{
.name = "dequeue",
- .read_map = blkiocg_dequeue_read,
+ .private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
+ BLKIO_PROP_dequeue),
+ .read_map = blkiocg_file_read_map,
},
#endif
};
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index 2b866ec..aa8f0ea 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -15,6 +15,11 @@
#include <linux/cgroup.h>
+enum blkio_policy_id {
+ BLKIO_POLICY_PROP = 0, /* Proportional Bandwidth division */
+ BLKIO_POLICY_THROTL, /* Throttling */
+};
+
#if defined(CONFIG_BLK_CGROUP) || defined(CONFIG_BLK_CGROUP_MODULE)
#ifndef CONFIG_BLK_CGROUP
@@ -65,6 +70,39 @@ enum blkg_state_flags {
BLKG_empty,
};
+/* cgroup files owned by proportional weight policy */
+enum blkcg_file_name_prop {
+ BLKIO_PROP_weight = 1,
+ BLKIO_PROP_weight_device,
+ BLKIO_PROP_io_service_bytes,
+ BLKIO_PROP_io_serviced,
+ BLKIO_PROP_time,
+ BLKIO_PROP_sectors,
+ BLKIO_PROP_io_service_time,
+ BLKIO_PROP_io_wait_time,
+ BLKIO_PROP_io_merged,
+ BLKIO_PROP_io_queued,
+ BLKIO_PROP_avg_queue_size,
+ BLKIO_PROP_group_wait_time,
+ BLKIO_PROP_idle_time,
+ BLKIO_PROP_empty_time,
+ BLKIO_PROP_dequeue,
+};
+
+/* cgroup files owned by throttle policy */
+enum blkcg_file_name_throtl {
+ BLKIO_THROTL_read_bps_device,
+ BLKIO_THROTL_write_bps_device,
+ BLKIO_THROTL_io_service_bytes,
+ BLKIO_THROTL_io_serviced,
+};
+
+enum blkio_rule_type {
+ BLKIO_RULE_WEIGHT = 0,
+ BLKIO_RULE_READ,
+ BLKIO_RULE_WRITE,
+};
+
struct blkio_cgroup {
struct cgroup_subsys_state css;
unsigned int weight;
@@ -113,6 +151,10 @@ struct blkio_group {
/* The device MKDEV(major, minor), this group has been created for */
dev_t dev;
+ /* policy which owns this blk group */
+ enum blkio_policy_id plid;
+
+
/* Need to serialize the stats in the case of reset/update */
spinlock_t stats_lock;
struct blkio_group_stats stats;
@@ -121,19 +163,44 @@ struct blkio_group {
struct blkio_policy_node {
struct list_head node;
dev_t dev;
- unsigned int weight;
+
+ /* This node belongs to max bw policy or porportional weight policy */
+ enum blkio_policy_id plid;
+
+ /* Whether a read or write rule */
+ enum blkio_rule_type rulet;
+
+ union {
+ unsigned int weight;
+ /*
+ * Rate read/write in terms of byptes per second
+ * Whether this rate represents read or write is determined
+ * by rule type "rulet"
+ */
+ u64 bps;
+ } val;
};
extern unsigned int blkcg_get_weight(struct blkio_cgroup *blkcg,
dev_t dev);
+extern uint64_t blkcg_get_read_bps(struct blkio_cgroup *blkcg,
+ dev_t dev);
+extern uint64_t blkcg_get_write_bps(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);
+typedef void (blkio_update_group_read_bps_fn) (struct blkio_group *blkg,
+ u64 read_bps);
+typedef void (blkio_update_group_write_bps_fn) (struct blkio_group *blkg,
+ u64 write_bps);
struct blkio_policy_ops {
blkio_unlink_group_fn *blkio_unlink_group_fn;
blkio_update_group_weight_fn *blkio_update_group_weight_fn;
+ blkio_update_group_read_bps_fn *blkio_update_group_read_bps_fn;
+ blkio_update_group_write_bps_fn *blkio_update_group_write_bps_fn;
};
struct blkio_policy_type {
@@ -212,7 +279,8 @@ static inline void blkiocg_set_start_empty_time(struct blkio_group *blkg) {}
extern struct blkio_cgroup blkio_root_cgroup;
extern struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup);
extern 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,
+ enum blkio_policy_id plid);
extern int blkiocg_del_blkio_group(struct blkio_group *blkg);
extern struct blkio_group *blkiocg_lookup_group(struct blkio_cgroup *blkcg,
void *key);
@@ -234,7 +302,8 @@ static inline struct blkio_cgroup *
cgroup_to_blkio_cgroup(struct cgroup *cgroup) { return NULL; }
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,
+ enum blkio_policy_id plid) {}
static inline int
blkiocg_del_blkio_group(struct blkio_group *blkg) { return 0; }
diff --git a/block/cfq.h b/block/cfq.h
index 93448e5..54a6d90 100644
--- a/block/cfq.h
+++ b/block/cfq.h
@@ -69,7 +69,7 @@ static inline void cfq_blkiocg_update_completion_stats(struct blkio_group *blkg,
static inline void cfq_blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
struct blkio_group *blkg, void *key, dev_t dev) {
- blkiocg_add_blkio_group(blkcg, blkg, key, dev);
+ blkiocg_add_blkio_group(blkcg, blkg, key, dev, BLKIO_POLICY_PROP);
}
static inline int cfq_blkiocg_del_blkio_group(struct blkio_group *blkg)
--
1.7.2.2
^ permalink raw reply [flat|nested] 5+ messages in thread* [PATCH 3/4] block: Core throttling logic implementation
2010-09-07 20:53 [RFC PATCH] Block device bio throttling support [V2] Vivek Goyal
2010-09-07 20:53 ` [PATCH 1/4] Kill the header printed at the start of blkio.weight_device file Vivek Goyal
2010-09-07 20:53 ` [PATCH 2/4] blkio: blkio cgroup interface related changes to support new throttling policy Vivek Goyal
@ 2010-09-07 20:53 ` Vivek Goyal
2010-09-07 20:53 ` [PATCH 4/4] blkio: Documentation update Vivek Goyal
3 siblings, 0 replies; 5+ messages in thread
From: Vivek Goyal @ 2010-09-07 20:53 UTC (permalink / raw)
To: linux-kernel, axboe; +Cc: nauman, dpshah, guijianfeng, vgoyal
o Actual implementation of throttling policy.
Signed-off-by: Vivek Goyal <vgoyal@redhat.com>
---
block/Kconfig | 12 +
block/Makefile | 1 +
block/blk-core.c | 24 ++
block/blk-throttle.c | 946 +++++++++++++++++++++++++++++++++++++++++++++
block/blk.h | 4 +-
block/cfq-iosched.c | 4 +
include/linux/blk_types.h | 3 +
include/linux/blkdev.h | 24 ++
init/Kconfig | 9 +-
9 files changed, 1023 insertions(+), 4 deletions(-)
create mode 100644 block/blk-throttle.c
diff --git a/block/Kconfig b/block/Kconfig
index 9be0b56..6c9213e 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -77,6 +77,18 @@ config BLK_DEV_INTEGRITY
T10/SCSI Data Integrity Field or the T13/ATA External Path
Protection. If in doubt, say N.
+config BLK_DEV_THROTTLING
+ bool "Block layer bio throttling support"
+ depends on BLK_CGROUP=y && EXPERIMENTAL
+ default n
+ ---help---
+ Block layer bio throttling support. It can be used to limit
+ the IO rate to a device. IO rate policies are per cgroup and
+ one needs to mount and use blkio cgroup controller for creating
+ cgroups and specifying per device IO rate policies.
+
+ See Documentation/cgroups/blkio-controller.txt for more information.
+
endif # BLOCK
config BLOCK_COMPAT
diff --git a/block/Makefile b/block/Makefile
index 0bb499a..c850d5e 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -9,6 +9,7 @@ obj-$(CONFIG_BLOCK) := elevator.o blk-core.o blk-tag.o blk-sysfs.o \
obj-$(CONFIG_BLK_DEV_BSG) += bsg.o
obj-$(CONFIG_BLK_CGROUP) += blk-cgroup.o
+obj-$(CONFIG_BLK_DEV_THROTTLING) += blk-throttle.o
obj-$(CONFIG_IOSCHED_NOOP) += noop-iosched.o
obj-$(CONFIG_IOSCHED_DEADLINE) += deadline-iosched.o
obj-$(CONFIG_IOSCHED_CFQ) += cfq-iosched.o
diff --git a/block/blk-core.c b/block/blk-core.c
index ee1a1e7..c4831b6 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -382,6 +382,7 @@ void blk_sync_queue(struct request_queue *q)
del_timer_sync(&q->unplug_timer);
del_timer_sync(&q->timeout);
cancel_work_sync(&q->unplug_work);
+ throtl_shutdown_timer_wq(q);
}
EXPORT_SYMBOL(blk_sync_queue);
@@ -459,6 +460,8 @@ void blk_cleanup_queue(struct request_queue *q)
if (q->elevator)
elevator_exit(q->elevator);
+ blk_throtl_exit(q);
+
blk_put_queue(q);
}
EXPORT_SYMBOL(blk_cleanup_queue);
@@ -515,6 +518,11 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
return NULL;
}
+ if (blk_throtl_init(q)) {
+ kmem_cache_free(blk_requestq_cachep, q);
+ return NULL;
+ }
+
setup_timer(&q->backing_dev_info.laptop_mode_wb_timer,
laptop_mode_timer_fn, (unsigned long) q);
init_timer(&q->unplug_timer);
@@ -1522,6 +1530,15 @@ static inline void __generic_make_request(struct bio *bio)
goto end_io;
}
+ blk_throtl_bio(q, &bio);
+
+ /*
+ * If bio = NULL, bio has been throttled and will be submitted
+ * later.
+ */
+ if (!bio)
+ break;
+
trace_block_bio_queue(q, bio);
ret = q->make_request_fn(q, bio);
@@ -2579,6 +2596,13 @@ int kblockd_schedule_work(struct request_queue *q, struct work_struct *work)
}
EXPORT_SYMBOL(kblockd_schedule_work);
+int kblockd_schedule_delayed_work(struct request_queue *q,
+ struct delayed_work *dwork, unsigned long delay)
+{
+ return queue_delayed_work(kblockd_workqueue, dwork, delay);
+}
+EXPORT_SYMBOL(kblockd_schedule_delayed_work);
+
int __init blk_dev_init(void)
{
BUILD_BUG_ON(__REQ_NR_BITS > 8 *
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
new file mode 100644
index 0000000..77ea2cf
--- /dev/null
+++ b/block/blk-throttle.c
@@ -0,0 +1,946 @@
+/*
+ * Interface for controlling IO bandwidth on a request queue
+ *
+ * Copyright (C) 2010 Vivek Goyal <vgoyal@redhat.com>
+ */
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/blkdev.h>
+#include <linux/bio.h>
+#include <linux/blktrace_api.h>
+#include "blk-cgroup.h"
+
+/* Max dispatch from a group in 1 round */
+static int throtl_grp_quantum = 8;
+
+/* Total max dispatch from all groups in one round */
+static int throtl_quantum = 32;
+
+/* Throttling is performed over 100ms slice and after that slice is renewed */
+static unsigned long throtl_slice = HZ/10; /* 100 ms */
+
+struct throtl_rb_root {
+ struct rb_root rb;
+ struct rb_node *left;
+ unsigned int count;
+ unsigned long min_disptime;
+};
+
+#define THROTL_RB_ROOT (struct throtl_rb_root) { .rb = RB_ROOT, .left = NULL, \
+ .count = 0, .min_disptime = 0}
+
+#define rb_entry_tg(node) rb_entry((node), struct throtl_grp, rb_node)
+
+struct throtl_grp {
+ /* List of throtl groups on the request queue*/
+ struct hlist_node tg_node;
+
+ /* active throtl group service_tree member */
+ struct rb_node rb_node;
+
+ /*
+ * Dispatch time in jiffies. This is the estimated time when group
+ * will unthrottle and is ready to dispatch more bio. It is used as
+ * key to sort active groups in service tree.
+ */
+ unsigned long disptime;
+
+ struct blkio_group blkg;
+ atomic_t ref;
+ unsigned int flags;
+
+ /* Two lists for READ and WRITE */
+ struct bio_list bio_lists[2];
+
+ /* Number of queued bios on READ and WRITE lists */
+ unsigned int nr_queued[2];
+
+ /* bytes per second rate limits */
+ uint64_t bps[2];
+
+ /* Number of bytes disptached in current slice */
+ uint64_t bytes_disp[2];
+
+ /* When did we start a new slice */
+ unsigned long slice_start[2];
+ unsigned long slice_end[2];
+};
+
+struct throtl_data
+{
+ /* List of throtl groups */
+ struct hlist_head tg_list;
+
+ /* service tree for active throtl groups */
+ struct throtl_rb_root tg_service_tree;
+
+ struct throtl_grp root_tg;
+ struct request_queue *queue;
+
+ /* Total Number of queued bios on READ and WRITE lists */
+ unsigned int nr_queued[2];
+
+ /* How many bios are on disp_list */
+ int nr_disp_list;
+
+ /*
+ * number of total undestroyed groups (excluding root group)
+ */
+ unsigned int nr_undestroyed_grps;
+
+ /* Bios queued for dispatch */
+ struct bio_list disp_list;
+
+ /* Work for dispatching throttled bios */
+ struct delayed_work throtl_work;
+};
+
+enum tg_state_flags {
+ THROTL_TG_FLAG_on_rr = 0, /* on round-robin busy list */
+};
+
+#define THROTL_TG_FNS(name) \
+static inline void throtl_mark_tg_##name(struct throtl_grp *tg) \
+{ \
+ (tg)->flags |= (1 << THROTL_TG_FLAG_##name); \
+} \
+static inline void throtl_clear_tg_##name(struct throtl_grp *tg) \
+{ \
+ (tg)->flags &= ~(1 << THROTL_TG_FLAG_##name); \
+} \
+static inline int throtl_tg_##name(const struct throtl_grp *tg) \
+{ \
+ return ((tg)->flags & (1 << THROTL_TG_FLAG_##name)) != 0; \
+}
+
+THROTL_TG_FNS(on_rr);
+
+#define throtl_log_tg(td, tg, fmt, args...) \
+ blk_add_trace_msg((td)->queue, "%s throtl " fmt, \
+ blkg_path(&(tg)->blkg), ##args); \
+
+#define throtl_log(td, fmt, args...) \
+ blk_add_trace_msg((td)->queue, "throtl " fmt, ##args)
+
+static inline struct throtl_grp *tg_of_blkg(struct blkio_group *blkg)
+{
+ if (blkg)
+ return container_of(blkg, struct throtl_grp, blkg);
+
+ return NULL;
+}
+
+static inline int total_nr_queued(struct throtl_data *td)
+{
+ return (td->nr_disp_list + td->nr_queued[0] + td->nr_queued[1]);
+}
+
+static inline struct throtl_grp *throtl_ref_get_tg(struct throtl_grp *tg)
+{
+ atomic_inc(&tg->ref);
+ return tg;
+}
+
+static void throtl_put_tg(struct throtl_grp *tg)
+{
+ BUG_ON(atomic_read(&tg->ref) <= 0);
+ if (!atomic_dec_and_test(&tg->ref))
+ return;
+ kfree(tg);
+}
+
+static struct throtl_grp * throtl_find_alloc_tg(struct throtl_data *td,
+ struct cgroup *cgroup)
+{
+ struct blkio_cgroup *blkcg = cgroup_to_blkio_cgroup(cgroup);
+ struct throtl_grp *tg = NULL;
+ void *key = td;
+ struct backing_dev_info *bdi = &td->queue->backing_dev_info;
+ unsigned int major, minor;
+
+ /*
+ * TODO: Speed up blkiocg_lookup_group() by maintaining a radix
+ * tree of blkg (instead of traversing through hash list all
+ * the time.
+ */
+ tg = tg_of_blkg(blkiocg_lookup_group(blkcg, key));
+
+ /* Fill in device details for root group */
+ if (tg && !tg->blkg.dev && bdi->dev && dev_name(bdi->dev)) {
+ sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor);
+ tg->blkg.dev = MKDEV(major, minor);
+ goto done;
+ }
+
+ if (tg)
+ goto done;
+
+ tg = kzalloc_node(sizeof(*tg), GFP_ATOMIC, td->queue->node);
+ if (!tg)
+ goto done;
+
+ INIT_HLIST_NODE(&tg->tg_node);
+ RB_CLEAR_NODE(&tg->rb_node);
+ bio_list_init(&tg->bio_lists[0]);
+ bio_list_init(&tg->bio_lists[1]);
+
+ /*
+ * Take the initial reference that will be released on destroy
+ * This can be thought of a joint reference by cgroup and
+ * request queue which will be dropped by either request queue
+ * exit or cgroup deletion path depending on who is exiting first.
+ */
+ atomic_set(&tg->ref, 1);
+
+ /* Add group onto cgroup list */
+ sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor);
+ blkiocg_add_blkio_group(blkcg, &tg->blkg, (void *)td,
+ MKDEV(major, minor), BLKIO_POLICY_THROTL);
+
+ tg->bps[READ] = blkcg_get_read_bps(blkcg, tg->blkg.dev);
+ tg->bps[WRITE] = blkcg_get_write_bps(blkcg, tg->blkg.dev);
+
+ hlist_add_head(&tg->tg_node, &td->tg_list);
+ td->nr_undestroyed_grps++;
+done:
+ return tg;
+}
+
+static struct throtl_grp * throtl_get_tg(struct throtl_data *td)
+{
+ struct cgroup *cgroup;
+ struct throtl_grp *tg = NULL;
+
+ rcu_read_lock();
+ cgroup = task_cgroup(current, blkio_subsys_id);
+ tg = throtl_find_alloc_tg(td, cgroup);
+ if (!tg)
+ tg = &td->root_tg;
+ rcu_read_unlock();
+ return tg;
+}
+
+static struct throtl_grp *throtl_rb_first(struct throtl_rb_root *root)
+{
+ /* Service tree is empty */
+ if (!root->count)
+ return NULL;
+
+ if (!root->left)
+ root->left = rb_first(&root->rb);
+
+ if (root->left)
+ return rb_entry_tg(root->left);
+
+ 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 throtl_rb_erase(struct rb_node *n, struct throtl_rb_root *root)
+{
+ if (root->left == n)
+ root->left = NULL;
+ rb_erase_init(n, &root->rb);
+ --root->count;
+}
+
+static void update_min_dispatch_time(struct throtl_rb_root *st)
+{
+ struct throtl_grp *tg;
+
+ tg = throtl_rb_first(st);
+ if (!tg)
+ return;
+
+ st->min_disptime = tg->disptime;
+}
+
+static void
+tg_service_tree_add(struct throtl_rb_root *st, struct throtl_grp *tg)
+{
+ struct rb_node **node = &st->rb.rb_node;
+ struct rb_node *parent = NULL;
+ struct throtl_grp *__tg;
+ unsigned long key = tg->disptime;
+ int left = 1;
+
+ while (*node != NULL) {
+ parent = *node;
+ __tg = rb_entry_tg(parent);
+
+ if (time_before(key, __tg->disptime))
+ node = &parent->rb_left;
+ else {
+ node = &parent->rb_right;
+ left = 0;
+ }
+ }
+
+ if (left)
+ st->left = &tg->rb_node;
+
+ rb_link_node(&tg->rb_node, parent, node);
+ rb_insert_color(&tg->rb_node, &st->rb);
+}
+
+static void __throtl_enqueue_tg(struct throtl_data *td, struct throtl_grp *tg)
+{
+ struct throtl_rb_root *st = &td->tg_service_tree;
+
+ tg_service_tree_add(st, tg);
+ throtl_mark_tg_on_rr(tg);
+ st->count++;
+}
+
+static void throtl_enqueue_tg(struct throtl_data *td, struct throtl_grp *tg)
+{
+ if (!throtl_tg_on_rr(tg))
+ __throtl_enqueue_tg(td, tg);
+}
+
+static void __throtl_dequeue_tg(struct throtl_data *td, struct throtl_grp *tg)
+{
+ throtl_rb_erase(&tg->rb_node, &td->tg_service_tree);
+ throtl_clear_tg_on_rr(tg);
+}
+
+static void throtl_dequeue_tg(struct throtl_data *td, struct throtl_grp *tg)
+{
+ if (throtl_tg_on_rr(tg))
+ __throtl_dequeue_tg(td, tg);
+}
+
+static void throtl_schedule_next_dispatch(struct throtl_data *td)
+{
+ struct throtl_rb_root *st = &td->tg_service_tree;
+
+ /*
+ * If there are more bios pending, schedule more work.
+ */
+ if (!total_nr_queued(td))
+ return;
+
+ BUG_ON(!st->count);
+
+ update_min_dispatch_time(st);
+
+ if (time_before_eq(st->min_disptime, jiffies))
+ throtl_schedule_delayed_work(td->queue, 0);
+ else
+ throtl_schedule_delayed_work(td->queue,
+ (st->min_disptime - jiffies));
+}
+
+static inline void
+throtl_start_new_slice(struct throtl_data *td, struct throtl_grp *tg, bool rw)
+{
+ tg->bytes_disp[rw] = 0;
+ tg->slice_start[rw] = jiffies;
+ tg->slice_end[rw] = jiffies + throtl_slice;
+ throtl_log_tg(td, tg, "[%c] new slice start=%lu end=%lu jiffies=%lu",
+ rw == READ ? 'R' : 'W', tg->slice_start[rw],
+ tg->slice_end[rw], jiffies);
+}
+
+static inline void throtl_extend_slice(struct throtl_data *td,
+ struct throtl_grp *tg, bool rw, unsigned long jiffy_end)
+{
+ tg->slice_end[rw] = roundup(jiffy_end, throtl_slice);
+ throtl_log_tg(td, tg, "[%c] extend slice start=%lu end=%lu jiffies=%lu",
+ rw == READ ? 'R' : 'W', tg->slice_start[rw],
+ tg->slice_end[rw], jiffies);
+}
+
+/* Trim the used slices and adjust slice start accordingly */
+static inline void
+throtl_trim_slice(struct throtl_data *td, struct throtl_grp *tg, bool rw)
+{
+ unsigned long nr_slices, bytes_trim, time_elapsed;
+
+ BUG_ON(time_before(tg->slice_end[rw], tg->slice_start[rw]));
+
+ time_elapsed = jiffies - tg->slice_start[rw];
+
+ nr_slices = time_elapsed / throtl_slice;
+
+ if (!nr_slices)
+ return;
+
+ bytes_trim = (tg->bps[rw] * throtl_slice * nr_slices)/HZ;
+
+ if (!bytes_trim)
+ return;
+
+ if (tg->bytes_disp[rw] >= bytes_trim)
+ tg->bytes_disp[rw] -= bytes_trim;
+ else
+ tg->bytes_disp[rw] = 0;
+
+ tg->slice_start[rw] += nr_slices * throtl_slice;
+
+ throtl_log_tg(td, tg, "[%c] trim slice nr=%lu bytes=%lu"
+ " start=%lu end=%lu jiffies=%lu",
+ rw == READ ? 'R' : 'W', nr_slices, bytes_trim,
+ tg->slice_start[rw], tg->slice_end[rw], jiffies);
+}
+
+/* Determine if previously allocated or extended slice is complete or not */
+static bool throtl_slice_used(struct throtl_data *td, struct throtl_grp *tg, bool rw)
+{
+ if (time_in_range(jiffies, tg->slice_start[rw], tg->slice_end[rw]))
+ return 0;
+
+ return 1;
+}
+
+/*
+ * Returns whether one can dispatch a bio or not. Also returns approx number
+ * of jiffies to wait before this bio is with-in IO rate and can be dispatched
+ */
+static bool tg_may_dispatch(struct throtl_data *td, struct throtl_grp *tg,
+ struct bio *bio, unsigned long *wait)
+{
+ bool rw = bio_data_dir(bio);
+ u64 bytes_allowed, extra_bytes;
+ unsigned long jiffy_elapsed, jiffy_wait, jiffy_elapsed_rnd;
+
+ /*
+ * Currently whole state machine of group depends on first bio
+ * queued in the group bio list. So one should not be calling
+ * this function with a different bio if there are other bios
+ * queued.
+ */
+ BUG_ON(tg->nr_queued[rw] && bio != bio_list_peek(&tg->bio_lists[rw]));
+
+ /* If tg->bps = -1, then BW is unlimited */
+ if (tg->bps[rw] == -1)
+ return 1;
+
+ /*
+ * If previous slice expired, start a new one otherwise renew/extend
+ * existing slice to make sure it is at least throtl_slice interval
+ * long since now.
+ */
+ if (throtl_slice_used(td, tg, rw))
+ throtl_start_new_slice(td, tg, rw);
+ else {
+ if (time_before(tg->slice_end[rw], jiffies + throtl_slice))
+ throtl_extend_slice(td, tg, rw, jiffies + throtl_slice);
+ }
+
+ jiffy_elapsed = jiffy_elapsed_rnd = jiffies - tg->slice_start[rw];
+
+ /* Slice has just started. Consider one slice interval */
+ if (!jiffy_elapsed)
+ jiffy_elapsed_rnd = throtl_slice;
+
+ jiffy_elapsed_rnd = roundup(jiffy_elapsed_rnd, throtl_slice);
+
+ bytes_allowed = (tg->bps[rw] * jiffies_to_msecs(jiffy_elapsed_rnd))
+ / MSEC_PER_SEC;
+
+ if (tg->bytes_disp[rw] + bio->bi_size <= bytes_allowed) {
+ if (wait)
+ *wait = 0;
+ return 1;
+ }
+
+ /* Calc approx time to dispatch */
+ extra_bytes = tg->bytes_disp[rw] + bio->bi_size - bytes_allowed;
+ jiffy_wait = div64_u64(extra_bytes * HZ, tg->bps[rw]);
+
+ if (!jiffy_wait)
+ jiffy_wait = 1;
+
+ /*
+ * This wait time is without taking into consideration the rounding
+ * up we did. Add that time also.
+ */
+ jiffy_wait = jiffy_wait + (jiffy_elapsed_rnd - jiffy_elapsed);
+
+ if (wait)
+ *wait = jiffy_wait;
+
+ if (time_before(tg->slice_end[rw], jiffies + jiffy_wait))
+ throtl_extend_slice(td, tg, rw, jiffies + jiffy_wait);
+
+ return 0;
+}
+
+static void throtl_charge_bio(struct throtl_grp *tg, struct bio *bio)
+{
+ bool rw = bio_data_dir(bio);
+ bool sync = bio->bi_rw & REQ_SYNC;
+
+ /* Charge the bio to the group */
+ tg->bytes_disp[rw] += bio->bi_size;
+
+ /*
+ * TODO: This will take blkg->stats_lock. Figure out a way
+ * to avoid this cost.
+ */
+ blkiocg_update_dispatch_stats(&tg->blkg, bio->bi_size, rw, sync);
+
+}
+
+static void throtl_add_bio_tg(struct throtl_data *td, struct throtl_grp *tg,
+ struct bio *bio)
+{
+ bool rw = bio_data_dir(bio);
+
+ bio_list_add(&tg->bio_lists[rw], bio);
+ /* Take a bio reference on tg */
+ throtl_ref_get_tg(tg);
+ tg->nr_queued[rw]++;
+ td->nr_queued[rw]++;
+ throtl_enqueue_tg(td, tg);
+}
+
+static void tg_update_disptime(struct throtl_data *td, struct throtl_grp *tg)
+{
+ unsigned long read_wait = -1, write_wait = -1, min_wait = -1, disptime;
+ struct bio *bio;
+
+ if ((bio = bio_list_peek(&tg->bio_lists[READ])))
+ tg_may_dispatch(td, tg, bio, &read_wait);
+
+ if ((bio = bio_list_peek(&tg->bio_lists[WRITE])))
+ tg_may_dispatch(td, tg, bio, &write_wait);
+
+ min_wait = min(read_wait, write_wait);
+ disptime = jiffies + min_wait;
+
+ /*
+ * If group is already on active tree, then update dispatch time
+ * only if it is lesser than existing dispatch time. Otherwise
+ * always update the dispatch time
+ */
+
+ if (throtl_tg_on_rr(tg) && time_before(disptime, tg->disptime))
+ return;
+
+ /* Update dispatch time */
+ throtl_dequeue_tg(td, tg);
+ tg->disptime = disptime;
+ throtl_enqueue_tg(td, tg);
+}
+
+static void
+tg_dispatch_one_bio(struct throtl_data *td, struct throtl_grp *tg, bool rw)
+{
+ struct bio *bio;
+
+ bio = bio_list_pop(&tg->bio_lists[rw]);
+ tg->nr_queued[rw]--;
+ /* Drop bio reference on tg */
+ throtl_put_tg(tg);
+
+ BUG_ON(td->nr_queued[rw] <= 0);
+ td->nr_queued[rw]--;
+
+ throtl_charge_bio(tg, bio);
+ bio_list_add(&td->disp_list, bio);
+ td->nr_disp_list++;
+
+ throtl_trim_slice(td, tg, rw);
+}
+
+/*
+ * Enter with queue lock held spin_lock_irq(). Returns with queue lock unlocked */
+static int release_from_disp_list(struct throtl_data *td)
+{
+ struct bio *bio;
+ unsigned int nr_disp = 0;
+
+ if (!td->nr_disp_list)
+ goto out;
+
+ while (!bio_list_empty(&td->disp_list)) {
+ bio = bio_list_pop(&td->disp_list);
+ bio->bi_rw |= REQ_THROTTLED;
+ BUG_ON(td->nr_disp_list <= 0);
+ td->nr_disp_list--;
+ nr_disp++;
+ /*
+ * Drop the spin lock and submit bio.
+ */
+ spin_unlock_irq(td->queue->queue_lock);
+ generic_make_request(bio);
+ spin_lock_irq(td->queue->queue_lock);
+ }
+
+out:
+ spin_unlock_irq(td->queue->queue_lock);
+ return nr_disp;
+}
+
+static int throtl_dispatch_tg(struct throtl_data *td, struct throtl_grp *tg)
+{
+ unsigned int nr_reads = 0, nr_writes = 0;
+ unsigned int max_nr_reads = throtl_grp_quantum*3/4;
+ unsigned int max_nr_writes = throtl_grp_quantum - nr_reads;
+ struct bio *bio;
+
+ /* Try to dispatch 75% READS and 25% WRITES */
+
+ while ((bio = bio_list_peek(&tg->bio_lists[READ]))
+ && tg_may_dispatch(td, tg, bio, NULL)) {
+
+ tg_dispatch_one_bio(td, tg, bio_data_dir(bio));
+ nr_reads++;
+
+ if (nr_reads >= max_nr_reads)
+ break;
+ }
+
+ while ((bio = bio_list_peek(&tg->bio_lists[WRITE]))
+ && tg_may_dispatch(td, tg, bio, NULL)) {
+
+ tg_dispatch_one_bio(td, tg, bio_data_dir(bio));
+ nr_writes++;
+
+ if (nr_writes >= max_nr_writes)
+ break;
+ }
+
+ return nr_reads + nr_writes;
+}
+
+static int throtl_select_dispatch(struct throtl_data *td)
+{
+ unsigned int nr_disp = 0;
+ struct throtl_grp *tg;
+ struct throtl_rb_root *st = &td->tg_service_tree;
+
+ while (1) {
+ tg = throtl_rb_first(st);
+
+ if (!tg)
+ break;
+
+ if (time_before(jiffies, tg->disptime))
+ break;
+
+ throtl_dequeue_tg(td, tg);
+
+ nr_disp += throtl_dispatch_tg(td, tg);
+
+ if (tg->nr_queued[0] || tg->nr_queued[1]) {
+ tg_update_disptime(td, tg);
+ throtl_enqueue_tg(td, tg);
+ }
+
+ if (nr_disp >= throtl_quantum)
+ break;
+ }
+
+ return nr_disp;
+}
+
+/* Dispatch throttled bios. Should be called without queue lock held. */
+static int throtl_dispatch(struct request_queue *q)
+{
+ struct throtl_data *td = q->td;
+ unsigned int nr_disp = 0, temp_disp = 0;
+
+ spin_lock_irq(q->queue_lock);
+
+ if (!total_nr_queued(td))
+ goto out;
+
+ throtl_log(td, "dispatch nr_queued=%lu", total_nr_queued(td));
+
+ while(1) {
+ temp_disp = 0;
+ temp_disp = release_from_disp_list(q->td);
+ nr_disp += temp_disp;
+
+ if (nr_disp >= throtl_quantum)
+ break;
+
+ /*
+ * release_from_disp_list returns with queue lock unlocked.
+ * acquire the lock again.
+ */
+ spin_lock_irq(q->queue_lock);
+ temp_disp = throtl_select_dispatch(td);
+ if (!temp_disp)
+ break;
+ }
+
+ throtl_schedule_next_dispatch(td);
+out:
+ spin_unlock_irq(q->queue_lock);
+ /*
+ * If we dispatched some requests, unplug the queue to make sure
+ * immediate dispatch
+ */
+ if (nr_disp) {
+ throtl_log(td, "bios disp=%u", nr_disp);
+ blk_unplug(q);
+ }
+ return nr_disp;
+}
+
+void blk_throtl_work(struct work_struct *work)
+{
+ struct throtl_data *td = container_of(work, struct throtl_data,
+ throtl_work.work);
+ struct request_queue *q = td->queue;
+
+ throtl_dispatch(q);
+}
+
+/* Call with queue lock held */
+void throtl_schedule_delayed_work(struct request_queue *q, unsigned long delay)
+{
+
+ struct throtl_data *td = q->td;
+ struct delayed_work *dwork = &td->throtl_work;
+
+ if (total_nr_queued(td) > 0) {
+ /*
+ * We might have a work scheduled to be executed in future.
+ * Cancel that and schedule a new one.
+ */
+ __cancel_delayed_work(dwork);
+ kblockd_schedule_delayed_work(q, dwork, delay);
+ throtl_log(td, "schedule work. delay=%lu jiffies=%lu",
+ delay, jiffies);
+ }
+}
+EXPORT_SYMBOL(throtl_schedule_delayed_work);
+
+static void
+throtl_destroy_tg(struct throtl_data *td, struct throtl_grp *tg)
+{
+ /* Something wrong if we are trying to remove same group twice */
+ BUG_ON(hlist_unhashed(&tg->tg_node));
+
+ hlist_del_init(&tg->tg_node);
+
+ /*
+ * Put the reference taken at the time of creation so that when all
+ * queues are gone, group can be destroyed.
+ */
+ throtl_put_tg(tg);
+ td->nr_undestroyed_grps--;
+}
+
+static void throtl_release_tgs(struct throtl_data *td)
+{
+ struct hlist_node *pos, *n;
+ struct throtl_grp *tg;
+
+ hlist_for_each_entry_safe(tg, pos, n, &td->tg_list, tg_node) {
+ /*
+ * If cgroup removal path got to blk_group first and removed
+ * it from cgroup list, then it will take care of destroying
+ * cfqg also.
+ */
+ if (!blkiocg_del_blkio_group(&tg->blkg))
+ throtl_destroy_tg(td, tg);
+ }
+}
+
+static void throtl_td_free(struct throtl_data *td)
+{
+ kfree(td);
+}
+
+/*
+ * Blk cgroup controller notification saying that blkio_group object is being
+ * delinked as associated cgroup object is going away. That also means that
+ * no new IO will come in this group. So get rid of this group as soon as
+ * any pending IO in the group is finished.
+ *
+ * This function is called under rcu_read_lock(). key is the rcu protected
+ * pointer. That means "key" is a valid throtl_data pointer as long as we are
+ * rcu read lock.
+ *
+ * "key" was fetched from blkio_group under blkio_cgroup->lock. That means
+ * it should not be NULL as even if queue was going away, cgroup deltion
+ * path got to it first.
+ */
+void throtl_unlink_blkio_group(void *key, struct blkio_group *blkg)
+{
+ unsigned long flags;
+ struct throtl_data *td = key;
+
+ spin_lock_irqsave(td->queue->queue_lock, flags);
+ throtl_destroy_tg(td, tg_of_blkg(blkg));
+ spin_unlock_irqrestore(td->queue->queue_lock, flags);
+}
+
+static void throtl_update_blkio_group_read_bps (struct blkio_group *blkg,
+ u64 read_bps)
+{
+ tg_of_blkg(blkg)->bps[READ] = read_bps;
+}
+
+static void throtl_update_blkio_group_write_bps (struct blkio_group *blkg,
+ u64 write_bps)
+{
+ tg_of_blkg(blkg)->bps[WRITE] = write_bps;
+}
+
+void throtl_shutdown_timer_wq(struct request_queue *q)
+{
+ struct throtl_data *td = q->td;
+
+ cancel_delayed_work_sync(&td->throtl_work);
+}
+
+static struct blkio_policy_type blkio_policy_throtl = {
+ .ops = {
+ .blkio_unlink_group_fn = throtl_unlink_blkio_group,
+ .blkio_update_group_read_bps_fn =
+ throtl_update_blkio_group_read_bps,
+ .blkio_update_group_write_bps_fn =
+ throtl_update_blkio_group_write_bps,
+ },
+};
+
+int blk_throtl_bio(struct request_queue *q, struct bio **biop)
+{
+ struct throtl_data *td = q->td;
+ struct throtl_grp *tg;
+ struct bio *bio = *biop;
+ bool rw = bio_data_dir(bio), update_disptime = true;
+
+ if (bio->bi_rw & REQ_THROTTLED) {
+ bio->bi_rw &= ~REQ_THROTTLED;
+ return 0;
+ }
+
+ /*
+ * Do not throttle barriers. Upstream work is on to get rid of
+ * hard barriers and block layer will not gurantee ordering of
+ * barrier w.r.t other bios, hence no need to flush all the
+ * queued/throttled bios.
+ */
+ if (unlikely((bio->bi_rw & REQ_HARDBARRIER)))
+ return 0;
+
+ spin_lock_irq(q->queue_lock);
+ tg = throtl_get_tg(td);
+
+ if (tg->nr_queued[rw]) {
+ /*
+ * There is already another bio queued in same dir. No
+ * need to update dispatch time.
+ */
+ update_disptime = false;
+ goto queue_bio;
+ }
+
+ /* Bio is with-in rate limit of group */
+ if (tg_may_dispatch(td, tg, bio, NULL)) {
+ throtl_charge_bio(tg, bio);
+ goto out;
+ }
+
+queue_bio:
+ throtl_log_tg(td, tg, "[%c] bio. disp=%u sz=%u bps=%llu"
+ " queued=%d/%d", rw == READ ? 'R' : 'W',
+ tg->bytes_disp[rw], bio->bi_size, tg->bps[rw],
+ tg->nr_queued[READ], tg->nr_queued[WRITE]);
+
+ throtl_add_bio_tg(q->td, tg, bio);
+ *biop = NULL;
+
+ if (update_disptime) {
+ tg_update_disptime(td, tg);
+ throtl_schedule_next_dispatch(td);
+ }
+
+out:
+ spin_unlock_irq(q->queue_lock);
+ return 0;
+}
+
+int blk_throtl_init(struct request_queue *q)
+{
+ struct throtl_data *td;
+ struct throtl_grp *tg;
+
+ td = kzalloc_node(sizeof(*td), GFP_KERNEL, q->node);
+ if (!td)
+ return -ENOMEM;
+
+ INIT_HLIST_HEAD(&td->tg_list);
+ td->tg_service_tree = THROTL_RB_ROOT;
+ bio_list_init(&td->disp_list);
+
+ /* Init root group */
+ tg = &td->root_tg;
+ INIT_HLIST_NODE(&tg->tg_node);
+ RB_CLEAR_NODE(&tg->rb_node);
+ bio_list_init(&tg->bio_lists[0]);
+ bio_list_init(&tg->bio_lists[1]);
+
+ /* Practically unlimited BW */
+ tg->bps[0] = tg->bps[1] = -1;
+ atomic_set(&tg->ref, 1);
+
+ INIT_DELAYED_WORK(&td->throtl_work, blk_throtl_work);
+
+ rcu_read_lock();
+ blkiocg_add_blkio_group(&blkio_root_cgroup, &tg->blkg, (void *)td,
+ 0, BLKIO_POLICY_THROTL);
+ rcu_read_unlock();
+
+ /* Attach throtl data to request queue */
+ td->queue = q;
+ q->td = td;
+ return 0;
+}
+
+void blk_throtl_exit(struct request_queue *q)
+{
+ struct throtl_data *td = q->td;
+ bool wait = false;
+
+ BUG_ON(!td);
+
+ throtl_shutdown_timer_wq(q);
+
+ spin_lock_irq(q->queue_lock);
+ throtl_release_tgs(td);
+ blkiocg_del_blkio_group(&td->root_tg.blkg);
+
+ /* If there are other groups */
+ if (td->nr_undestroyed_grps >= 1)
+ wait = true;
+
+ spin_unlock_irq(q->queue_lock);
+
+ /*
+ * Wait for tg->blkg->key accessors to exit their grace periods.
+ * Do this wait only if there are other undestroyed groups out
+ * there (other than root group). This can happen if cgroup deletion
+ * path claimed the responsibility of cleaning up a group before
+ * queue cleanup code get to the group.
+ *
+ * Do not call synchronize_rcu() unconditionally as there are drivers
+ * which create/delete request queue hundreds of times during scan/boot
+ * and synchronize_rcu() can take significant time and slow down boot.
+ */
+ if (wait)
+ synchronize_rcu();
+ throtl_td_free(td);
+}
+
+static int __init throtl_init(void)
+{
+ blkio_policy_register(&blkio_policy_throtl);
+ return 0;
+}
+
+module_init(throtl_init);
diff --git a/block/blk.h b/block/blk.h
index 6e7dc87..e836e64 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -62,8 +62,10 @@ static inline struct request *__elv_next_request(struct request_queue *q)
return rq;
}
- if (!q->elevator->ops->elevator_dispatch_fn(q, 0))
+ if (!q->elevator->ops->elevator_dispatch_fn(q, 0)) {
+ throtl_schedule_delayed_work(q, 0);
return NULL;
+ }
}
}
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index eb4086f..8cec3a8 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -467,10 +467,14 @@ static inline bool cfq_bio_sync(struct bio *bio)
*/
static inline void cfq_schedule_dispatch(struct cfq_data *cfqd)
{
+ struct request_queue *q = cfqd->queue;
+
if (cfqd->busy_queues) {
cfq_log(cfqd, "schedule dispatch");
kblockd_schedule_work(cfqd->queue, &cfqd->unplug_work);
}
+
+ throtl_schedule_delayed_work(q, 0);
}
static int cfq_queue_empty(struct request_queue *q)
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index ca83a97..10a0c29 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -130,6 +130,8 @@ enum rq_flag_bits {
/* bio only flags */
__REQ_UNPLUG, /* unplug the immediately after submission */
__REQ_RAHEAD, /* read ahead, can fail anytime */
+ __REQ_THROTTLED, /* This bio has already been subjected to
+ * throttling rules. Don't do it again. */
/* request only flags */
__REQ_SORTED, /* elevator knows about this request */
@@ -172,6 +174,7 @@ enum rq_flag_bits {
#define REQ_UNPLUG (1 << __REQ_UNPLUG)
#define REQ_RAHEAD (1 << __REQ_RAHEAD)
+#define REQ_THROTTLED (1 << __REQ_THROTTLED)
#define REQ_SORTED (1 << __REQ_SORTED)
#define REQ_SOFTBARRIER (1 << __REQ_SOFTBARRIER)
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 2c54906..66bca1a 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -367,6 +367,11 @@ struct request_queue
#if defined(CONFIG_BLK_DEV_BSG)
struct bsg_class_device bsg_dev;
#endif
+
+#ifdef CONFIG_BLK_DEV_THROTTLING
+ /* Throttle data */
+ struct throtl_data *td;
+#endif
};
#define QUEUE_FLAG_CLUSTER 0 /* cluster several segments into 1 */
@@ -1127,6 +1132,7 @@ static inline void put_dev_sector(Sector p)
struct work_struct;
int kblockd_schedule_work(struct request_queue *q, struct work_struct *work);
+int kblockd_schedule_delayed_work(struct request_queue *q, struct delayed_work *dwork, unsigned long delay);
#ifdef CONFIG_BLK_CGROUP
/*
@@ -1170,6 +1176,24 @@ static inline uint64_t rq_io_start_time_ns(struct request *req)
}
#endif
+#ifdef CONFIG_BLK_DEV_THROTTLING
+extern int blk_throtl_init(struct request_queue *q);
+extern void blk_throtl_exit(struct request_queue *q);
+extern int blk_throtl_bio(struct request_queue *q, struct bio **bio);
+extern void throtl_schedule_delayed_work(struct request_queue *q, unsigned long delay);
+extern void throtl_shutdown_timer_wq(struct request_queue *q);
+#else /* CONFIG_BLK_DEV_THROTTLING */
+static inline int blk_throtl_bio(struct request_queue *q, struct bio **bio)
+{
+ return 0;
+}
+
+static inline int blk_throtl_init(struct request_queue *q) { return 0; }
+static inline int blk_throtl_exit(struct request_queue *q) { return 0; }
+static inline void throtl_schedule_delayed_work(struct request_queue *q, unsigned long delay) {}
+static inline void throtl_shutdown_timer_wq(struct request_queue *q) {}
+#endif /* CONFIG_BLK_DEV_THROTTLING */
+
#define MODULE_ALIAS_BLOCKDEV(major,minor) \
MODULE_ALIAS("block-major-" __stringify(major) "-" __stringify(minor))
#define MODULE_ALIAS_BLOCKDEV_MAJOR(major) \
diff --git a/init/Kconfig b/init/Kconfig
index 2de5b1c..950ba26 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -634,11 +634,14 @@ config BLK_CGROUP
Currently, CFQ IO scheduler uses it to recognize task groups and
control disk bandwidth allocation (proportional time slice allocation)
- to such task groups.
+ to such task groups. It is also used by bio throttling logic in
+ block layer to implement upper limit in IO rates on a device.
This option only enables generic Block IO controller infrastructure.
- One needs to also enable actual IO controlling logic in CFQ for it
- to take effect. (CONFIG_CFQ_GROUP_IOSCHED=y).
+ One needs to also enable actual IO controlling logic/policy. For
+ enabling proportional weight division of disk bandwidth in CFQ seti
+ CONFIG_CFQ_GROUP_IOSCHED=y and for enabling throttling policy set
+ CONFIG_BLK_THROTTLE=y.
See Documentation/cgroups/blkio-controller.txt for more information.
--
1.7.2.2
^ permalink raw reply [flat|nested] 5+ messages in thread