[PATCH 12/16] blkio: Export disk time and sectors used by a group to user space

From: Vivek Goyal
Date: Thu Nov 12 2009 - 18:46:22 EST

Next message: Randy Dunlap: "[PATCH -next] staging/line6: fix printk formats"
Previous message: Greg KH: "Re: [PATCH] Devices that ignore USB spec generate invalidmodaliases"
In reply to: Vivek Goyal: "[PATCH 07/16] blkio: Introduce per cfq group weights and vdisktime calculations"
Next in thread: Vivek Goyal: "[PATCH 08/16] blkio: Group time used accounting and workload context save restore"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

o Export disk time and sector used by a group to user space through cgroup
interface.

o Also export a "dequeue" interface to cgroup which keeps track of how many
a times a group was deleted from service tree. Helps in debugging.

Signed-off-by: Vivek Goyal <vgoyal@xxxxxxxxxx>
---
block/blk-cgroup.c | 64 ++++++++++++++++++++++++++++++++++++++++++++++++++-
block/blk-cgroup.h | 22 ++++++++++++++++-
block/cfq-iosched.c | 23 ++++++++++++++----
3 files changed, 101 insertions(+), 8 deletions(-)

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 6bc99a3..4ef78d3 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -11,6 +11,8 @@
* Nauman Rafique <nauman@xxxxxxxxxx>
*/
#include <linux/ioprio.h>
+#include <linux/seq_file.h>
+#include <linux/kdev_t.h>
#include "blk-cgroup.h"

extern void cfq_unlink_blkio_group(void *, struct blkio_group *);
@@ -23,8 +25,15 @@ struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup)
struct blkio_cgroup, css);
}

+void blkiocg_update_blkio_group_stats(struct blkio_group *blkg,
+ unsigned long time, unsigned long sectors)
+{
+ blkg->time += time;
+ blkg->sectors += sectors;
+}
+
void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
- struct blkio_group *blkg, void *key)
+ struct blkio_group *blkg, void *key, dev_t dev)
{
unsigned long flags;

@@ -37,6 +46,7 @@ void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
/* Need to take css reference ? */
cgroup_path(blkcg->css.cgroup, blkg->path, sizeof(blkg->path));
#endif
+ blkg->dev = dev;
}

static void __blkiocg_del_blkio_group(struct blkio_group *blkg)
@@ -115,12 +125,64 @@ blkiocg_weight_write(struct cgroup *cgroup, struct cftype *cftype, u64 val)
return 0;
}

+#define SHOW_FUNCTION_PER_GROUP(__VAR) \
+static int blkiocg_##__VAR##_read(struct cgroup *cgroup, \
+ struct cftype *cftype, struct seq_file *m) \
+{ \
+ struct blkio_cgroup *blkcg; \
+ struct blkio_group *blkg; \
+ struct hlist_node *n; \
+ \
+ 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) \
+ seq_printf(m, "%u:%u %lu\n", MAJOR(blkg->dev), \
+ MINOR(blkg->dev), blkg->__VAR); \
+ } \
+ rcu_read_unlock(); \
+ cgroup_unlock(); \
+ return 0; \
+}
+
+SHOW_FUNCTION_PER_GROUP(time);
+SHOW_FUNCTION_PER_GROUP(sectors);
+#ifdef CONFIG_DEBUG_BLK_CGROUP
+SHOW_FUNCTION_PER_GROUP(dequeue);
+#endif
+#undef SHOW_FUNCTION_PER_GROUP
+
+#ifdef CONFIG_DEBUG_BLK_CGROUP
+void blkiocg_update_blkio_group_dequeue_stats(struct blkio_group *blkg,
+ unsigned long dequeue)
+{
+ blkg->dequeue += dequeue;
+}
+#endif
+
struct cftype blkio_files[] = {
{
.name = "weight",
.read_u64 = blkiocg_weight_read,
.write_u64 = blkiocg_weight_write,
},
+ {
+ .name = "time",
+ .read_seq_string = blkiocg_time_read,
+ },
+ {
+ .name = "sectors",
+ .read_seq_string = blkiocg_sectors_read,
+ },
+#ifdef CONFIG_DEBUG_BLK_CGROUP
+ {
+ .name = "dequeue",
+ .read_seq_string = blkiocg_dequeue_read,
+ },
+#endif
};

static int blkiocg_populate(struct cgroup_subsys *subsys, struct cgroup *cgroup)
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index 3573199..b24ab71 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -30,7 +30,15 @@ struct blkio_group {
#ifdef CONFIG_DEBUG_BLK_CGROUP
/* Store cgroup path */
char path[128];
+ /* How many times this group has been removed from service tree */
+ unsigned long dequeue;
#endif
+ /* The device MKDEV(major, minor), this group has been created for */
+ dev_t dev;
+
+ /* total disk time and nr sectors dispatched by this group */
+ unsigned long time;
+ unsigned long sectors;
};

#define BLKIO_WEIGHT_MIN 100
@@ -42,24 +50,30 @@ static inline char *blkg_path(struct blkio_group *blkg)
{
return blkg->path;
}
+void blkiocg_update_blkio_group_dequeue_stats(struct blkio_group *blkg,
+ unsigned long dequeue);
#else
static inline char *blkg_path(struct blkio_group *blkg) { return NULL; }
+static inline void blkiocg_update_blkio_group_dequeue_stats(
+ struct blkio_group *blkg, unsigned long dequeue) {}
#endif

#ifdef CONFIG_BLK_CGROUP
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);
+ struct blkio_group *blkg, void *key, dev_t dev);
extern int blkiocg_del_blkio_group(struct blkio_group *blkg);
extern struct blkio_group *blkiocg_lookup_group(struct blkio_cgroup *blkcg,
void *key);
+void blkiocg_update_blkio_group_stats(struct blkio_group *blkg,
+ unsigned long time, unsigned long sectors);
#else
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)
+ struct blkio_group *blkg, void *key, dev_t dev)
{
}

@@ -68,5 +82,9 @@ blkiocg_del_blkio_group(struct blkio_group *blkg) { return 0; }

static inline struct blkio_group *
blkiocg_lookup_group(struct blkio_cgroup *blkcg, void *key) { return NULL; }
+static inline void blkiocg_update_blkio_group_stats(struct blkio_group *blkg,
+ unsigned long time, unsigned long sectors)
+{
+}
#endif
#endif /* _BLK_CGROUP_H */
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 6b30a6b..24640f1 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -141,6 +141,8 @@ struct cfq_queue {
struct cfq_rb_root *service_tree;
struct cfq_queue *new_cfqq;
struct cfq_group *cfqg;
+ /* Sectors dispatched in current dispatch round */
+ unsigned long nr_sectors;
};

/*
@@ -815,6 +817,7 @@ cfq_group_service_tree_del(struct cfq_data *cfqd, struct cfq_group *cfqg)
if (!RB_EMPTY_NODE(&cfqg->rb_node))
cfq_rb_erase(&cfqg->rb_node, st);
cfqg->saved_workload_slice = 0;
+ blkiocg_update_blkio_group_dequeue_stats(&cfqg->blkg, 1);
}

static inline unsigned long cfq_cfqq_slice_usage(struct cfq_queue *cfqq)
@@ -841,12 +844,13 @@ static inline unsigned long cfq_cfqq_slice_usage(struct cfq_queue *cfqq)
slice_used = allocated_slice;
}

- cfq_log_cfqq(cfqq->cfqd, cfqq, "sl_used=%lu", slice_used);
+ cfq_log_cfqq(cfqq->cfqd, cfqq, "sl_used=%lu sect=%lu", slice_used,
+ cfqq->nr_sectors);
return slice_used;
}

static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg,
- unsigned long service)
+ unsigned long service, unsigned long sectors)
{
struct cfq_rb_root *st = &cfqd->grp_service_tree;

@@ -866,6 +870,7 @@ static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg,

cfq_log_cfqg(cfqd, cfqg, "served: vt=%llu min_vt=%llu", cfqg->vdisktime,
st->min_vdisktime);
+ blkiocg_update_blkio_group_stats(&cfqg->blkg, service, sectors);
}

#ifdef CONFIG_CFQ_GROUP_IOSCHED
@@ -883,6 +888,8 @@ cfq_find_alloc_cfqg(struct cfq_data *cfqd, struct cgroup *cgroup, int create)
struct cfq_group *cfqg = NULL;
void *key = cfqd;
int i, j;
+ unsigned int major, minor;
+ struct backing_dev_info *bdi = &cfqd->queue->backing_dev_info;

/* Do we need to take this reference */
if (!css_tryget(&blkcg->css))
@@ -913,7 +920,9 @@ cfq_find_alloc_cfqg(struct cfq_data *cfqd, struct cgroup *cgroup, int create)
atomic_set(&cfqg->ref, 1);

/* Add group onto cgroup list */
- blkiocg_add_blkio_group(blkcg, &cfqg->blkg, (void *)cfqd);
+ sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor);
+ blkiocg_add_blkio_group(blkcg, &cfqg->blkg, (void *)cfqd,
+ MKDEV(major, minor));

/* Add group on cfqd list */
hlist_add_head(&cfqg->cfqd_node, &cfqd->cfqg_list);
@@ -1450,6 +1459,7 @@ static void __cfq_set_active_queue(struct cfq_data *cfqd,
cfqq->dispatch_start = jiffies;
cfqq->slice_end = 0;
cfqq->slice_dispatch = 0;
+ cfqq->nr_sectors = 0;

cfq_clear_cfqq_wait_request(cfqq);
cfq_clear_cfqq_must_dispatch(cfqq);
@@ -1485,7 +1495,8 @@ __cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq,
cfq_log_cfqq(cfqd, cfqq, "resid=%ld", cfqq->slice_resid);
}

- cfq_group_served(cfqd, cfqq->cfqg, cfq_cfqq_slice_usage(cfqq));
+ cfq_group_served(cfqd, cfqq->cfqg, cfq_cfqq_slice_usage(cfqq),
+ cfqq->nr_sectors);

if (cfq_cfqq_on_rr(cfqq) && RB_EMPTY_ROOT(&cfqq->sort_list))
cfq_del_cfqq_rr(cfqd, cfqq);
@@ -1798,6 +1809,7 @@ static void cfq_dispatch_insert(struct request_queue *q, struct request *rq)

if (cfq_cfqq_sync(cfqq))
cfqd->sync_flight++;
+ cfqq->nr_sectors += blk_rq_sectors(rq);
}

/*
@@ -3492,7 +3504,8 @@ static void *cfq_init_queue(struct request_queue *q)
* to make sure that cfq_put_cfqg() does not try to kfree root group
*/
atomic_set(&cfqg->ref, 1);
- blkiocg_add_blkio_group(&blkio_root_cgroup, &cfqg->blkg, (void *)cfqd);
+ blkiocg_add_blkio_group(&blkio_root_cgroup, &cfqg->blkg, (void *)cfqd,
+ 0);
#endif
/*
* Not strictly needed (since RB_ROOT just clears the node and we
--
1.6.2.5

--
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/

Next message: Randy Dunlap: "[PATCH -next] staging/line6: fix printk formats"
Previous message: Greg KH: "Re: [PATCH] Devices that ignore USB spec generate invalidmodaliases"
In reply to: Vivek Goyal: "[PATCH 07/16] blkio: Introduce per cfq group weights and vdisktime calculations"
Next in thread: Vivek Goyal: "[PATCH 08/16] blkio: Group time used accounting and workload context save restore"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]