[PATCH 18/20] io-controller: Support per cgroup per device weights and io class

From: Vivek Goyal
Date: Fri Jun 19 2009 - 16:41:31 EST


This patch enables per-cgroup per-device weight and ioprio_class handling.
A new cgroup interface "policy" is introduced. You can make use of this
file to configure weight and ioprio_class for each device in a given cgroup.
The original "weight" and "ioprio_class" files are still available. If you
don't do special configuration for a particular device, "weight" and
"ioprio_class" are used as default values in this device.

You can use the following format to play with the new interface.
#echo DEV:weight:ioprio_class > /patch/to/cgroup/policy
weight=0 means removing the policy for DEV.

Examples:
Configure weight=300 ioprio_class=2 on /dev/hdb in this cgroup
# echo /dev/hdb:300:2 > io.policy
# cat io.policy
dev weight class
/dev/hdb 300 2

Configure weight=500 ioprio_class=1 on /dev/hda in this cgroup
# echo /dev/hda:500:1 > io.policy
# cat io.policy
dev weight class
/dev/hda 500 1
/dev/hdb 300 2

Remove the policy for /dev/hda in this cgroup
# echo /dev/hda:0:1 > io.policy
# cat io.policy
dev weight class
/dev/hdb 300 2

Changelog (v1 -> v2)
- Rename some structures
- Use spin_lock_irqsave() and spin_lock_irqrestore() version to prevent
from enabling the interrupts unconditionally.
- Fix policy setup bug when switching to another io scheduler.
- If a policy is available for a specific device, don't update weight and
io class when writing "weight" and "iprio_class".
- Fix a bug when parsing policy string.

Signed-off-by: Gui Jianfeng <guijianfeng@xxxxxxxxxxxxxx>
Signed-off-by: Vivek Goyal <vgoyal@xxxxxxxxxx>
---
block/elevator-fq.c | 243 ++++++++++++++++++++++++++++++++++++++++++++++++++-
block/elevator-fq.h | 11 +++
2 files changed, 250 insertions(+), 4 deletions(-)

diff --git a/block/elevator-fq.c b/block/elevator-fq.c
index 13c8161..326f955 100644
--- a/block/elevator-fq.c
+++ b/block/elevator-fq.c
@@ -15,6 +15,7 @@
#include <linux/blktrace_api.h>
#include <linux/seq_file.h>
#include <linux/biotrack.h>
+#include <linux/genhd.h>

/* Values taken from cfq */
const int elv_slice_sync = HZ / 10;
@@ -1168,12 +1169,31 @@ struct io_group *io_cgroup_lookup_group(struct io_cgroup *iocg, void *key)
return NULL;
}

-void io_group_init_entity(struct io_cgroup *iocg, struct io_group *iog)
+static struct io_policy_node *policy_search_node(const struct io_cgroup *iocg,
+ dev_t dev);
+
+void io_group_init_entity(struct io_cgroup *iocg, struct io_group *iog,
+ dev_t dev)
{
struct io_entity *entity = &iog->entity;
+ struct io_policy_node *pn;
+ unsigned long flags;
+
+ spin_lock_irqsave(&iocg->lock, flags);
+ pn = policy_search_node(iocg, dev);
+ if (pn) {
+ entity->weight = pn->weight;
+ entity->new_weight = pn->weight;
+ entity->ioprio_class = pn->ioprio_class;
+ entity->new_ioprio_class = pn->ioprio_class;
+ } else {
+ entity->weight = iocg->weight;
+ entity->new_weight = iocg->weight;
+ entity->ioprio_class = iocg->ioprio_class;
+ entity->new_ioprio_class = iocg->ioprio_class;
+ }
+ spin_unlock_irqrestore(&iocg->lock, flags);

- entity->weight = entity->new_weight = iocg->weight;
- entity->ioprio_class = entity->new_ioprio_class = iocg->ioprio_class;
entity->ioprio_changed = 1;
entity->my_sched_data = &iog->sched_data;
}
@@ -1225,6 +1245,7 @@ static int io_cgroup_##__VAR##_write(struct cgroup *cgroup, \
struct io_cgroup *iocg; \
struct io_group *iog; \
struct hlist_node *n; \
+ struct io_policy_node *pn; \
\
if (val < (__MIN) || val > (__MAX)) \
return -EINVAL; \
@@ -1237,6 +1258,9 @@ static int io_cgroup_##__VAR##_write(struct cgroup *cgroup, \
spin_lock_irq(&iocg->lock); \
iocg->__VAR = (unsigned long)val; \
hlist_for_each_entry(iog, n, &iocg->group_data, group_node) { \
+ pn = policy_search_node(iocg, iog->dev); \
+ if (pn) \
+ continue; \
iog->entity.new_##__VAR = (unsigned long)val; \
smp_wmb(); \
iog->entity.ioprio_changed = 1; \
@@ -1352,7 +1376,7 @@ struct io_group *io_group_chain_alloc(struct request_queue *q, void *key,
sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor);
iog->dev = MKDEV(major, minor);

- io_group_init_entity(iocg, iog);
+ io_group_init_entity(iocg, iog, iog->dev);
iog->my_entity = &iog->entity;

atomic_set(&iog->ref, 0);
@@ -1665,8 +1689,212 @@ struct io_group *io_alloc_root_group(struct request_queue *q,
return iog;
}

+static int io_cgroup_policy_read(struct cgroup *cgrp, struct cftype *cft,
+ struct seq_file *m)
+{
+ struct io_cgroup *iocg;
+ struct io_policy_node *pn;
+
+ iocg = cgroup_to_io_cgroup(cgrp);
+
+ if (list_empty(&iocg->policy_list))
+ goto out;
+
+ seq_printf(m, "dev weight class\n");
+
+ spin_lock_irq(&iocg->lock);
+ list_for_each_entry(pn, &iocg->policy_list, node) {
+ seq_printf(m, "%s %lu %lu\n", pn->dev_name,
+ pn->weight, pn->ioprio_class);
+ }
+ spin_unlock_irq(&iocg->lock);
+out:
+ return 0;
+}
+
+static inline void policy_insert_node(struct io_cgroup *iocg,
+ struct io_policy_node *pn)
+{
+ list_add(&pn->node, &iocg->policy_list);
+}
+
+/* Must be called with iocg->lock held */
+static inline void policy_delete_node(struct io_policy_node *pn)
+{
+ list_del(&pn->node);
+}
+
+/* Must be called with iocg->lock held */
+static struct io_policy_node *policy_search_node(const struct io_cgroup *iocg,
+ dev_t dev)
+{
+ struct io_policy_node *pn;
+
+ if (list_empty(&iocg->policy_list))
+ return NULL;
+
+ list_for_each_entry(pn, &iocg->policy_list, node) {
+ if (pn->dev == dev)
+ return pn;
+ }
+
+ return NULL;
+}
+
+static int devname_to_devnum(const char *buf, dev_t *dev)
+{
+ struct block_device *bdev;
+ struct gendisk *disk;
+ int part;
+
+ bdev = lookup_bdev(buf);
+ if (IS_ERR(bdev))
+ return -ENODEV;
+
+ disk = get_gendisk(bdev->bd_dev, &part);
+ if (part)
+ return -EINVAL;
+
+ *dev = MKDEV(disk->major, disk->first_minor);
+ bdput(bdev);
+
+ return 0;
+}
+
+static int policy_parse_and_set(char *buf, struct io_policy_node *newpn)
+{
+ char *s[3], *p;
+ int ret;
+ int i = 0;
+
+ memset(s, 0, sizeof(s));
+ while ((p = strsep(&buf, ":")) != NULL) {
+ if (!*p)
+ continue;
+ s[i++] = p;
+ }
+
+ ret = devname_to_devnum(s[0], &newpn->dev);
+ if (ret)
+ return ret;
+
+ strcpy(newpn->dev_name, s[0]);
+
+ if (s[1] == NULL)
+ return -EINVAL;
+
+ ret = strict_strtoul(s[1], 10, &newpn->weight);
+ if (ret || newpn->weight > WEIGHT_MAX)
+ return -EINVAL;
+
+ if (s[2] == NULL)
+ return -EINVAL;
+
+ ret = strict_strtoul(s[2], 10, &newpn->ioprio_class);
+ if (ret || newpn->ioprio_class < IOPRIO_CLASS_RT ||
+ newpn->ioprio_class > IOPRIO_CLASS_IDLE)
+ return -EINVAL;
+
+ return 0;
+}
+
+static int io_cgroup_policy_write(struct cgroup *cgrp, struct cftype *cft,
+ const char *buffer)
+{
+ struct io_cgroup *iocg;
+ struct io_policy_node *newpn, *pn;
+ char *buf;
+ int ret = 0;
+ int keep_newpn = 0;
+ struct hlist_node *n;
+ struct io_group *iog;
+
+ buf = kstrdup(buffer, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+
+ newpn = kzalloc(sizeof(*newpn), GFP_KERNEL);
+ if (!newpn) {
+ ret = -ENOMEM;
+ goto free_buf;
+ }
+
+ ret = policy_parse_and_set(buf, newpn);
+ if (ret)
+ goto free_newpn;
+
+ if (!cgroup_lock_live_group(cgrp)) {
+ ret = -ENODEV;
+ goto free_newpn;
+ }
+
+ iocg = cgroup_to_io_cgroup(cgrp);
+ spin_lock_irq(&iocg->lock);
+
+ pn = policy_search_node(iocg, newpn->dev);
+ if (!pn) {
+ if (newpn->weight != 0) {
+ policy_insert_node(iocg, newpn);
+ keep_newpn = 1;
+ }
+ goto update_io_group;
+ }
+
+ if (newpn->weight == 0) {
+ /* weight == 0 means deleteing a policy */
+ policy_delete_node(pn);
+ goto update_io_group;
+ }
+
+ pn->weight = newpn->weight;
+ pn->ioprio_class = newpn->ioprio_class;
+
+update_io_group:
+ hlist_for_each_entry(iog, n, &iocg->group_data, group_node) {
+ if (iog->dev == newpn->dev) {
+ if (newpn->weight) {
+ iog->entity.new_weight = newpn->weight;
+ iog->entity.new_ioprio_class =
+ newpn->ioprio_class;
+ /*
+ * iog weight and ioprio_class updating
+ * actually happens if ioprio_changed is set.
+ * So ensure ioprio_changed is not set until
+ * new weight and new ioprio_class are updated.
+ */
+ smp_wmb();
+ iog->entity.ioprio_changed = 1;
+ } else {
+ iog->entity.new_weight = iocg->weight;
+ iog->entity.new_ioprio_class =
+ iocg->ioprio_class;
+
+ /* The same as above */
+ smp_wmb();
+ iog->entity.ioprio_changed = 1;
+ }
+ }
+ }
+ spin_unlock_irq(&iocg->lock);
+
+ cgroup_unlock();
+
+free_newpn:
+ if (!keep_newpn)
+ kfree(newpn);
+free_buf:
+ kfree(buf);
+ return ret;
+}
+
struct cftype bfqio_files[] = {
{
+ .name = "policy",
+ .read_seq_string = io_cgroup_policy_read,
+ .write_string = io_cgroup_policy_write,
+ .max_write_len = 256,
+ },
+ {
.name = "weight",
.read_u64 = io_cgroup_weight_read,
.write_u64 = io_cgroup_weight_write,
@@ -1708,6 +1936,7 @@ struct cgroup_subsys_state *iocg_create(struct cgroup_subsys *subsys,
INIT_HLIST_HEAD(&iocg->group_data);
iocg->weight = IO_DEFAULT_GRP_WEIGHT;
iocg->ioprio_class = IO_DEFAULT_GRP_CLASS;
+ INIT_LIST_HEAD(&iocg->policy_list);

return &iocg->css;
}
@@ -1911,6 +2140,7 @@ void iocg_destroy(struct cgroup_subsys *subsys, struct cgroup *cgroup)
struct io_group *iog;
struct elv_fq_data *efqd;
unsigned long uninitialized_var(flags);
+ struct io_policy_node *pn, *pntmp;

/*
* io groups are linked in two lists. One list is maintained
@@ -1949,6 +2179,11 @@ remove_entry:
goto remove_entry;

done:
+ list_for_each_entry_safe(pn, pntmp, &iocg->policy_list, node) {
+ policy_delete_node(pn);
+ kfree(pn);
+ }
+
free_css_id(&io_subsys, &iocg->css);
rcu_read_unlock();
BUG_ON(!hlist_empty(&iocg->group_data));
diff --git a/block/elevator-fq.h b/block/elevator-fq.h
index d60105f..7102455 100644
--- a/block/elevator-fq.h
+++ b/block/elevator-fq.h
@@ -267,6 +267,14 @@ struct io_group {
struct rcu_head rcu_head;
};

+struct io_policy_node {
+ struct list_head node;
+ char dev_name[32];
+ dev_t dev;
+ unsigned long weight;
+ unsigned long ioprio_class;
+};
+
/**
* struct bfqio_cgroup - bfq cgroup data structure.
* @css: subsystem state for bfq in the containing cgroup.
@@ -283,6 +291,9 @@ struct io_cgroup {

unsigned long weight, ioprio_class;

+ /* list of io_policy_node */
+ struct list_head policy_list;
+
spinlock_t lock;
struct hlist_head group_data;
};
--
1.6.0.6

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/