[PATCH 9/9] blkio-cgroup-v9: Add a cgroup support to dm-ioband

From: Ryo Tsuruta
Date: Tue Jul 21 2009 - 10:25:22 EST

With this patch, dm-ioband can work with the blkio-cgroup.

Signed-off-by: Hirokazu Takahashi <taka@xxxxxxxxxxxxx>
Signed-off-by: Ryo Tsuruta <ryov@xxxxxxxxxxxxx>

---
drivers/md/dm-ioband-ctl.c | 211 ++++++++++++++++++++++++++++++++++++++++-
drivers/md/dm-ioband-policy.c | 20 +++
drivers/md/dm-ioband-rangebw.c | 13 ++
drivers/md/dm-ioband-type.c | 10 -
drivers/md/dm-ioband.h | 14 ++
drivers/md/dm-ioctl.c | 1
include/linux/biotrack.h | 7 +
mm/biotrack.c | 119 ++++++++++++++++++++++-
8 files changed, 382 insertions(+), 13 deletions(-)

Index: linux-2.6.31-rc3/include/linux/biotrack.h
===================================================================
--- linux-2.6.31-rc3.orig/include/linux/biotrack.h
+++ linux-2.6.31-rc3/include/linux/biotrack.h
@@ -9,6 +9,7 @@

struct io_context;
struct block_device;
+struct ioband_cgroup_ops;

struct blkio_cgroup {
struct cgroup_subsys_state css;
@@ -49,6 +50,12 @@ extern void blkio_cgroup_copy_owner(stru
extern struct io_context *get_blkio_cgroup_iocontext(struct bio *bio);
extern unsigned long get_blkio_cgroup_id(struct bio *bio);
extern struct cgroup *blkio_cgroup_lookup(int id);
+extern int blkio_cgroup_register_ioband(const struct ioband_cgroup_ops *ops);
+
+static inline int blkio_cgroup_unregister_ioband(void)
+{
+ return blkio_cgroup_register_ioband(NULL);
+}

#else /* !CONFIG_CGROUP_BLKIO */

Index: linux-2.6.31-rc3/mm/biotrack.c
===================================================================
--- linux-2.6.31-rc3.orig/mm/biotrack.c
+++ linux-2.6.31-rc3/mm/biotrack.c
@@ -21,6 +21,9 @@
#include <linux/blkdev.h>
#include <linux/biotrack.h>
#include <linux/mm_inline.h>
+#include <linux/seq_file.h>
+#include <linux/dm-ioctl.h>
+#include <../drivers/md/dm-ioband.h>

/*
* The block I/O tracking mechanism is implemented on the cgroup memory
@@ -50,6 +53,8 @@ static struct blkio_cgroup default_blkio
.id = 0,
.io_context = &default_blkio_io_context,
};
+static DEFINE_MUTEX(ioband_ops_lock);
+static const struct ioband_cgroup_ops *ioband_ops = NULL;

/**
* blkio_cgroup_set_owner() - set the owner ID of a page.
@@ -206,6 +211,11 @@ static void blkio_cgroup_destroy(struct
{
struct blkio_cgroup *biog = cgroup_blkio(cgrp);

+ mutex_lock(&ioband_ops_lock);
+ if (ioband_ops)
+ ioband_ops->remove_group(biog);
+ mutex_unlock(&ioband_ops_lock);
+
put_io_context(biog->io_context);

spin_lock_irq(&blkio_cgroup_idr_lock);
@@ -292,23 +302,128 @@ struct cgroup *blkio_cgroup_lookup(int i
return NULL;
return biog->css.cgroup;
}
+
+/**
+ * blkio_cgroup_register_ioband() - register ioband
+ * @p: a pointer to struct ioband_cgroup_ops
+ *
+ * Calling with NULL means unregistration.
+ * Returns 0 on success.
+ */
+int blkio_cgroup_register_ioband(const struct ioband_cgroup_ops *p)
+{
+ if (blkio_cgroup_disabled())
+ return -1;
+
+ mutex_lock(&ioband_ops_lock);
+ ioband_ops = p;
+ mutex_unlock(&ioband_ops_lock);
+ return 0;
+}
EXPORT_SYMBOL(get_blkio_cgroup_iocontext);
EXPORT_SYMBOL(get_blkio_cgroup_id);
EXPORT_SYMBOL(blkio_cgroup_lookup);
+EXPORT_SYMBOL(blkio_cgroup_register_ioband);

+/* Read the ID of the specified blkio cgroup. */
static u64 blkio_id_read(struct cgroup *cgrp, struct cftype *cft)
{
- struct blkio_cgroup *biog = cgroup_blkio(cgrp);
+ struct blkio_cgroup *biog;
+ int id;
+
+ biog = cgroup_blkio(cgrp);
+ id = biog->id;
+
+ return (u64) id;
+}
+
+/* Show all ioband devices and their settings. */
+static int blkio_devs_read(struct cgroup *cgrp, struct cftype *cft,
+ struct seq_file *m)
+{
+ mutex_lock(&ioband_ops_lock);
+ if (ioband_ops)
+ ioband_ops->show_device(m);
+ mutex_unlock(&ioband_ops_lock);
+ return 0;
+}
+
+/* Configure ioband devices specified by an ioband device ID */
+static int blkio_devs_write(struct cgroup *cgrp, struct cftype *cft,
+ const char *buffer)
+{
+ char **argv;
+ int argc, r = 0;

- return (u64) biog->id;
+ if (cgrp != cgrp->top_cgroup)
+ return -EACCES;
+
+ argv = argv_split(GFP_KERNEL, buffer, &argc);
+ if (!argv)
+ return -ENOMEM;
+
+ mutex_lock(&ioband_ops_lock);
+ if (ioband_ops)
+ r = ioband_ops->config_device(argc, argv);
+ mutex_unlock(&ioband_ops_lock);
+
+ argv_free(argv);
+ return r;
}

+/* Show the settings of the specified blkio cgroup. */
+static int blkio_settings_read(struct cgroup *cgrp, struct cftype *cft,
+ struct seq_file *m)
+{
+ struct blkio_cgroup *biog;
+
+ mutex_lock(&ioband_ops_lock);
+ if (ioband_ops) {
+ biog = cgroup_blkio(cgrp);
+ ioband_ops->show_group(m, biog);
+ }
+ mutex_unlock(&ioband_ops_lock);
+ return 0;
+}
+
+/* Configure the specified blkio cgroup. */
+static int blkio_settings_write(struct cgroup *cgrp, struct cftype *cft,
+ const char *buffer)
+{
+ struct blkio_cgroup *biog;
+ char **argv;
+ int argc, r = 0;
+
+ argv = argv_split(GFP_KERNEL, buffer, &argc);
+ if (!argv)
+ return -ENOMEM;
+
+ mutex_lock(&ioband_ops_lock);
+ if (ioband_ops) {
+ biog = cgroup_blkio(cgrp);
+ r = ioband_ops->config_group(argc, argv, biog);
+ }
+ mutex_unlock(&ioband_ops_lock);
+
+ argv_free(argv);
+ return r;
+}

static struct cftype blkio_files[] = {
{
.name = "id",
.read_u64 = blkio_id_read,
},
+ {
+ .name = "devices",
+ .read_seq_string = blkio_devs_read,
+ .write_string = blkio_devs_write,
+ },
+ {
+ .name = "settings",
+ .read_seq_string = blkio_settings_read,
+ .write_string = blkio_settings_write,
+ },
};

static int blkio_cgroup_populate(struct cgroup_subsys *ss, struct cgroup *cgrp)
Index: linux-2.6.31-rc3/drivers/md/dm-ioctl.c
===================================================================
--- linux-2.6.31-rc3.orig/drivers/md/dm-ioctl.c
+++ linux-2.6.31-rc3/drivers/md/dm-ioctl.c
@@ -1601,3 +1601,4 @@ out:

return r;
}
+EXPORT_SYMBOL(dm_copy_name_and_uuid);
Index: linux-2.6.31-rc3/drivers/md/dm-ioband-policy.c
===================================================================
--- linux-2.6.31-rc3.orig/drivers/md/dm-ioband-policy.c
+++ linux-2.6.31-rc3/drivers/md/dm-ioband-policy.c
@@ -8,6 +8,7 @@
#include <linux/bio.h>
#include <linux/workqueue.h>
#include <linux/rbtree.h>
+#include <linux/seq_file.h>
#include "dm.h"
#include "dm-ioband.h"

@@ -276,7 +277,7 @@ static int policy_weight_param(struct io
if (value)
err = strict_strtol(value, 0, &val);

- if (!strcmp(cmd, "weight")) {
+ if (!cmd || !strcmp(cmd, "weight")) {
if (!value)
set_weight(gp, DEFAULT_WEIGHT);
else if (!err && 0 < val && val <= SHORT_MAX)
@@ -341,6 +342,19 @@ static void policy_weight_show(struct io
*szp = sz;
}

+static void policy_weight_show_device(struct seq_file *m,
+ struct ioband_device *dp)
+{
+ seq_printf(m, " token=%d carryover=%d",
+ dp->g_token_bucket, dp->g_carryover);
+}
+
+static void policy_weight_show_group(struct seq_file *m,
+ struct ioband_group *gp)
+{
+ seq_printf(m, " weight=%d", gp->c_weight);
+}
+
/*
* <Method> <description>
* g_can_submit : To determine whether a given group has the right to
@@ -369,6 +383,8 @@ static void policy_weight_show(struct io
* Return 1 if a given group can't receive any more BIOs,
* otherwise return 0.
* g_show : Show the configuration.
+ * g_show_device : Show the configuration of the specified ioband device.
+ * g_show_group : Show the configuration of the spacified ioband group.
*/
static int policy_weight_init(struct ioband_device *dp, int argc, char **argv)
{
@@ -391,6 +407,8 @@ static int policy_weight_init(struct iob
dp->g_set_param = policy_weight_param;
dp->g_should_block = is_queue_full;
dp->g_show = policy_weight_show;
+ dp->g_show_device = policy_weight_show_device;
+ dp->g_show_group = policy_weight_show_group;

dp->g_epoch = 0;
dp->g_weight_total = 0;
Index: linux-2.6.31-rc3/drivers/md/dm-ioband-rangebw.c
===================================================================
--- linux-2.6.31-rc3.orig/drivers/md/dm-ioband-rangebw.c
+++ linux-2.6.31-rc3/drivers/md/dm-ioband-rangebw.c
@@ -25,6 +25,7 @@
#include <linux/random.h>
#include <linux/time.h>
#include <linux/timer.h>
+#include <linux/seq_file.h>
#include "dm.h"
#include "md.h"
#include "dm-ioband.h"
@@ -459,7 +460,7 @@ static int policy_range_bw_param(struct
err++;
}

- if (!strcmp(cmd, "range-bw")) {
+ if (!cmd || !strcmp(cmd, "range-bw")) {
if (!err && 0 <= min_val &&
min_val <= (INT_MAX / 2) && 0 <= max_val &&
max_val <= (INT_MAX / 2) && min_val <= max_val)
@@ -547,6 +548,12 @@ static void policy_range_bw_show(struct
*szp = sz;
}

+static void policy_range_bw_show_group(struct seq_file *m,
+ struct ioband_group *gp)
+{
+ seq_printf(m, " range-bw=%d:%d", gp->c_min_bw, gp->c_max_bw);
+}
+
static int range_bw_prepare_token(struct ioband_group *gp,
struct bio *bio, int flag)
{
@@ -633,6 +640,8 @@ void range_bw_timeover(unsigned long gp)
* Return 1 if a given group can't receive any more BIOs,
* otherwise return 0.
* g_show : Show the configuration.
+ * g_show_device : Show the configuration of the specified ioband device.
+ * g_show_group : Show the configuration of the spacified ioband group.
*/

int policy_range_bw_init(struct ioband_device *dp, int argc, char **argv)
@@ -656,6 +665,8 @@ int policy_range_bw_init(struct ioband_d
dp->g_set_param = policy_range_bw_param;
dp->g_should_block = range_bw_queue_full;
dp->g_show = policy_range_bw_show;
+ dp->g_show_device = NULL;
+ dp->g_show_group = policy_range_bw_show_group;

dp->g_min_bw_total = 0;
dp->g_running_gp = NULL;
Index: linux-2.6.31-rc3/drivers/md/dm-ioband-ctl.c
===================================================================
--- linux-2.6.31-rc3.orig/drivers/md/dm-ioband-ctl.c
+++ linux-2.6.31-rc3/drivers/md/dm-ioband-ctl.c
@@ -15,6 +15,8 @@
#include <linux/slab.h>
#include <linux/workqueue.h>
#include <linux/rbtree.h>
+#include <linux/biotrack.h>
+#include <linux/dm-ioctl.h>
#include "dm.h"
#include "md.h"
#include "dm-ioband.h"
@@ -111,6 +113,7 @@ static struct ioband_device *alloc_ioban
INIT_DELAYED_WORK(&new_dp->g_conductor, ioband_conduct);
INIT_LIST_HEAD(&new_dp->g_groups);
INIT_LIST_HEAD(&new_dp->g_list);
+ INIT_LIST_HEAD(&new_dp->g_heads);
spin_lock_init(&new_dp->g_lock);
bio_list_init(&new_dp->g_urgent_bios);
new_dp->g_io_throttle = io_throttle;
@@ -243,6 +246,7 @@ static int ioband_group_init(struct ioba
int r;

INIT_LIST_HEAD(&gp->c_list);
+ INIT_LIST_HEAD(&gp->c_heads);
bio_list_init(&gp->c_blocked_bios);
bio_list_init(&gp->c_prio_bios);
gp->c_id = id; /* should be verified */
@@ -273,7 +277,8 @@ static int ioband_group_init(struct ioba
ioband_group_add_node(&head->c_group_root, gp);
gp->c_dev = head->c_dev;
gp->c_target = head->c_target;
- }
+ } else
+ list_add_tail(&gp->c_heads, &dp->g_heads);

spin_unlock_irqrestore(&dp->g_lock, flags);
return 0;
@@ -287,6 +292,8 @@ static void ioband_group_release(struct
list_del(&gp->c_list);
if (head)
rb_erase(&gp->c_group_node, &head->c_group_root);
+ else
+ list_del(&gp->c_heads);
dp->g_group_dtr(gp);
kfree(gp);
}
@@ -1290,6 +1297,201 @@ static struct target_type ioband_target
.merge = ioband_merge,
};

+#ifdef CONFIG_CGROUP_BLKIO
+/* Read the ID of the specified blkio cgroup. */
+static void ioband_copy_name(struct ioband_group *gp, char *name)
+{
+ struct mapped_device *md;
+
+ md = dm_table_get_md(gp->c_target->table);
+ dm_copy_name_and_uuid(md, name, NULL);
+ dm_put(md);
+}
+
+/* Show all ioband devices and their settings. */
+static void ioband_cgroup_show_device(struct seq_file *m)
+{
+ struct ioband_device *dp;
+ struct ioband_group *gp;
+ char name[DM_NAME_LEN];
+
+ mutex_lock(&ioband_lock);
+
+ list_for_each_entry(dp, &ioband_device_list, g_list) {
+ seq_printf(m, "%s policy=%s io_throttle=%d io_limit=%d",
+ dp->g_name, dp->g_policy->p_name,
+ dp->g_io_throttle, dp->g_io_limit);
+ if (dp->g_show_device)
+ dp->g_show_device(m, dp);
+ seq_putc(m, '\n');
+
+ list_for_each_entry(gp, &dp->g_heads, c_heads) {
+ if (strcmp(gp->c_type->t_name, "cgroup"))
+ continue;
+ ioband_copy_name(gp, name);
+ seq_printf(m, " %s\n", name);
+ }
+ }
+
+ mutex_unlock(&ioband_lock);
+}
+
+/* Configure ioband devices specified by an ioband device ID */
+static int ioband_cgroup_config_device(int argc, char **argv)
+{
+ struct ioband_device *dp;
+ struct ioband_group *gp;
+ char name[DM_NAME_LEN];
+ int r;
+
+ if (argc < 1)
+ return -EINVAL;
+
+ mutex_lock(&ioband_lock);
+
+ /* look up the ioband device */
+ list_for_each_entry(dp, &ioband_device_list, g_list) {
+ /* assuming argv[0] is a share name */
+ if (!strcmp(dp->g_name, argv[0])) {
+ gp = list_first_entry(&dp->g_heads,
+ struct ioband_group, c_heads);
+ goto found;
+ }
+
+ /* assuming argv[0] is a device name */
+ list_for_each_entry(gp, &dp->g_heads, c_heads) {
+ ioband_copy_name(gp, name);
+ if (!strcmp(name, argv[0]))
+ goto found;
+ }
+ }
+
+ mutex_unlock(&ioband_lock);
+ return -ENODEV;
+
+found:
+ if (!strcmp(gp->c_type->t_name, "cgroup"))
+ r = __ioband_message(gp->c_target, --argc, &argv[1]);
+ else
+ r = -ENODEV;
+
+ mutex_unlock(&ioband_lock);
+ return r;
+}
+
+/* Show the settings of the specified blkio cgroup. */
+static void ioband_cgroup_show_group(struct seq_file *m,
+ struct blkio_cgroup *biog)
+{
+ struct ioband_device *dp;
+ struct ioband_group *head, *gp;
+ struct cgroup *cgrp = biog->css.cgroup;
+ char name[DM_NAME_LEN];
+
+ mutex_lock(&ioband_lock);
+
+ list_for_each_entry(dp, &ioband_device_list, g_list) {
+ list_for_each_entry(head, &dp->g_heads, c_heads) {
+ if (strcmp(head->c_type->t_name, "cgroup"))
+ continue;
+
+ if (cgrp == cgrp->top_cgroup)
+ gp = head;
+ else {
+ gp = ioband_group_find(head, biog->id);
+ if (!gp)
+ continue;
+ }
+
+ ioband_copy_name(head, name);
+ seq_puts(m, name);
+ if (dp->g_show_group)
+ dp->g_show_group(m, gp);
+ seq_putc(m, '\n');
+ }
+ }
+
+ mutex_unlock(&ioband_lock);
+}
+
+/* Configure the specified blkio cgroup. */
+static int ioband_cgroup_config_group(int argc, char **argv,
+ struct blkio_cgroup *biog)
+{
+ struct ioband_device *dp;
+ struct ioband_group *head, *gp;
+ struct cgroup *cgrp = biog->css.cgroup;
+ char name[DM_NAME_LEN];
+ int r;
+
+ if (argc != 1 && argc != 2)
+ return -EINVAL;
+
+ mutex_lock(&ioband_lock);
+
+ list_for_each_entry(dp, &ioband_device_list, g_list) {
+ list_for_each_entry(head, &dp->g_heads, c_heads) {
+ if (strcmp(head->c_type->t_name, "cgroup"))
+ continue;
+ ioband_copy_name(head, name);
+ if (!strcmp(name, argv[0]))
+ goto found;
+ }
+ }
+
+ mutex_unlock(&ioband_lock);
+ return -ENODEV;
+
+found:
+ if (argc == 1) {
+ if (cgrp == cgrp->top_cgroup)
+ r = -EINVAL;
+ else
+ r = ioband_group_detach(head, biog->id);
+ } else {
+ if (cgrp == cgrp->top_cgroup)
+ gp = head;
+ else
+ gp = ioband_group_find(head, biog->id);
+
+ if (!gp)
+ r = ioband_group_attach(head, biog->id, argv[1]);
+ else
+ r = gp->c_banddev->g_set_param(gp, NULL, argv[1]);
+ }
+
+ mutex_unlock(&ioband_lock);
+ return r;
+}
+
+/* Remove the specified blkio cgroup. */
+static void ioband_cgroup_remove_group(struct blkio_cgroup *biog)
+{
+ struct ioband_device *dp;
+ struct ioband_group *head;
+
+ mutex_lock(&ioband_lock);
+
+ list_for_each_entry(dp, &ioband_device_list, g_list) {
+ list_for_each_entry(head, &dp->g_heads, c_heads) {
+ if (strcmp(head->c_type->t_name, "cgroup"))
+ continue;
+ ioband_group_detach(head, biog->id);
+ }
+ }
+
+ mutex_unlock(&ioband_lock);
+}
+
+static const struct ioband_cgroup_ops ioband_ops = {
+ .show_device = ioband_cgroup_show_device,
+ .config_device = ioband_cgroup_config_device,
+ .show_group = ioband_cgroup_show_group,
+ .config_group = ioband_cgroup_config_group,
+ .remove_group = ioband_cgroup_remove_group,
+};
+#endif
+
static int __init dm_ioband_init(void)
{
int r;
@@ -1297,11 +1499,18 @@ static int __init dm_ioband_init(void)
r = dm_register_target(&ioband_target);
if (r < 0)
DMERR("register failed %d", r);
+#ifdef CONFIG_CGROUP_BLKIO
+ else
+ r = blkio_cgroup_register_ioband(&ioband_ops);
+#endif
return r;
}

static void __exit dm_ioband_exit(void)
{
+#ifdef CONFIG_CGROUP_BLKIO
+ blkio_cgroup_unregister_ioband();
+#endif
dm_unregister_target(&ioband_target);
}

Index: linux-2.6.31-rc3/drivers/md/dm-ioband.h
===================================================================
--- linux-2.6.31-rc3.orig/drivers/md/dm-ioband.h
+++ linux-2.6.31-rc3/drivers/md/dm-ioband.h
@@ -44,6 +44,7 @@ struct ioband_device {

int g_ref;
struct list_head g_list;
+ struct list_head g_heads;
int g_flags;
char g_name[IOBAND_NAME_MAX + 1];
const struct ioband_policy_type *g_policy;
@@ -59,6 +60,8 @@ struct ioband_device {
int (*g_set_param) (struct ioband_group *, const char *, const char *);
int (*g_should_block) (struct ioband_group *);
void (*g_show) (struct ioband_group *, int *, char *, unsigned);
+ void (*g_show_device) (struct seq_file *, struct ioband_device *);
+ void (*g_show_group) (struct seq_file *, struct ioband_group *);

/* members for weight balancing policy */
int g_epoch;
@@ -104,6 +107,7 @@ struct ioband_group_stat {

struct ioband_group {
struct list_head c_list;
+ struct list_head c_heads;
struct ioband_device *c_banddev;
struct dm_dev *c_dev;
struct dm_target *c_target;
@@ -150,6 +154,16 @@ struct ioband_group {

};

+struct blkio_cgroup;
+
+struct ioband_cgroup_ops {
+ void (*show_device)(struct seq_file *);
+ int (*config_device)(int, char **);
+ void (*show_group)(struct seq_file *, struct blkio_cgroup *);
+ int (*config_group)(int, char **, struct blkio_cgroup *);
+ void (*remove_group)(struct blkio_cgroup *);
+};
+
#define IOBAND_URGENT 1

#define DEV_BIO_BLOCKED 1
Index: linux-2.6.31-rc3/drivers/md/dm-ioband-type.c
===================================================================
--- linux-2.6.31-rc3.orig/drivers/md/dm-ioband-type.c
+++ linux-2.6.31-rc3/drivers/md/dm-ioband-type.c
@@ -6,6 +6,7 @@
* This file is released under the GPL.
*/
#include <linux/bio.h>
+#include <linux/biotrack.h>
#include "dm.h"
#include "dm-ioband.h"

@@ -52,14 +53,7 @@ static int ioband_node(struct bio *bio)

static int ioband_cgroup(struct bio *bio)
{
- /*
- * This function should return the ID of the cgroup which
- * issued "bio". The ID of the cgroup which the current
- * process belongs to won't be suitable ID for this purpose,
- * since some BIOs will be handled by kernel threads like aio
- * or pdflush on behalf of the process requesting the BIOs.
- */
- return 0; /* not implemented yet */
+ return get_blkio_cgroup_id(bio);
}

const struct ioband_group_type dm_ioband_group_type[] = {
--
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/