summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorVivek Goyal <vgoyal@redhat.com>2009-12-03 12:59:43 -0500
committerJens Axboe <jens.axboe@oracle.com>2009-12-03 19:28:52 +0100
commit25bc6b07767fe77422312eda2af99c9477f76191 (patch)
tree1e0f2d5a18efb63c651df8773a6d5ad2b87d7687
parent31e4c28d95e64f2d5d3c497a3ecf37c62de635b4 (diff)
downloadop-kernel-dev-25bc6b07767fe77422312eda2af99c9477f76191.zip
op-kernel-dev-25bc6b07767fe77422312eda2af99c9477f76191.tar.gz
blkio: Introduce per cfq group weights and vdisktime calculations
o Bring in the per cfq group weight and how vdisktime is calculated for the group. Also bring in the functionality of updating the min_vdisktime of the group service tree. Signed-off-by: Vivek Goyal <vgoyal@redhat.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
-rw-r--r--block/Kconfig.iosched9
-rw-r--r--block/cfq-iosched.c62
2 files changed, 69 insertions, 2 deletions
diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched
index be0280d..fa95fa7 100644
--- a/block/Kconfig.iosched
+++ b/block/Kconfig.iosched
@@ -23,7 +23,6 @@ config IOSCHED_DEADLINE
config IOSCHED_CFQ
tristate "CFQ I/O scheduler"
- select BLK_CGROUP
default y
---help---
The CFQ I/O scheduler tries to distribute bandwidth equally
@@ -33,6 +32,14 @@ config IOSCHED_CFQ
This is the default I/O scheduler.
+config CFQ_GROUP_IOSCHED
+ bool "CFQ Group Scheduling support"
+ depends on IOSCHED_CFQ && CGROUPS
+ select BLK_CGROUP
+ default n
+ ---help---
+ Enable group IO scheduling in CFQ.
+
choice
prompt "Default I/O scheduler"
default DEFAULT_CFQ
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index e1f822a..019f28e 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -13,6 +13,7 @@
#include <linux/rbtree.h>
#include <linux/ioprio.h>
#include <linux/blktrace_api.h>
+#include "blk-cgroup.h"
/*
* tunables
@@ -49,6 +50,7 @@ static const int cfq_hist_divisor = 4;
#define CFQ_SLICE_SCALE (5)
#define CFQ_HW_QUEUE_MIN (5)
+#define CFQ_SERVICE_SHIFT 12
#define RQ_CIC(rq) \
((struct cfq_io_context *) (rq)->elevator_private)
@@ -79,6 +81,7 @@ struct cfq_rb_root {
struct rb_node *left;
unsigned count;
u64 min_vdisktime;
+ struct rb_node *active;
};
#define CFQ_RB_ROOT (struct cfq_rb_root) { RB_ROOT, NULL, 0, 0, }
@@ -163,6 +166,7 @@ struct cfq_group {
/* group service_tree key */
u64 vdisktime;
+ unsigned int weight;
bool on_st;
/* number of cfqq currently on this group */
@@ -434,6 +438,51 @@ cfq_prio_to_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
return cfq_prio_slice(cfqd, cfq_cfqq_sync(cfqq), cfqq->ioprio);
}
+static inline u64 cfq_scale_slice(unsigned long delta, struct cfq_group *cfqg)
+{
+ u64 d = delta << CFQ_SERVICE_SHIFT;
+
+ d = d * BLKIO_WEIGHT_DEFAULT;
+ do_div(d, cfqg->weight);
+ return d;
+}
+
+static inline u64 max_vdisktime(u64 min_vdisktime, u64 vdisktime)
+{
+ s64 delta = (s64)(vdisktime - min_vdisktime);
+ if (delta > 0)
+ min_vdisktime = vdisktime;
+
+ return min_vdisktime;
+}
+
+static inline u64 min_vdisktime(u64 min_vdisktime, u64 vdisktime)
+{
+ s64 delta = (s64)(vdisktime - min_vdisktime);
+ if (delta < 0)
+ min_vdisktime = vdisktime;
+
+ return min_vdisktime;
+}
+
+static void update_min_vdisktime(struct cfq_rb_root *st)
+{
+ u64 vdisktime = st->min_vdisktime;
+ struct cfq_group *cfqg;
+
+ if (st->active) {
+ cfqg = rb_entry_cfqg(st->active);
+ vdisktime = cfqg->vdisktime;
+ }
+
+ if (st->left) {
+ cfqg = rb_entry_cfqg(st->left);
+ vdisktime = min_vdisktime(vdisktime, cfqg->vdisktime);
+ }
+
+ st->min_vdisktime = max_vdisktime(st->min_vdisktime, vdisktime);
+}
+
/*
* get averaged number of queues of RT/BE priority.
* average is updated, with a formula that gives more weight to higher numbers,
@@ -734,8 +783,12 @@ cfq_group_service_tree_del(struct cfq_data *cfqd, struct cfq_group *cfqg)
{
struct cfq_rb_root *st = &cfqd->grp_service_tree;
+ if (st->active == &cfqg->rb_node)
+ st->active = NULL;
+
BUG_ON(cfqg->nr_cfqq < 1);
cfqg->nr_cfqq--;
+
/* If there are other cfq queues under this group, don't delete it */
if (cfqg->nr_cfqq)
return;
@@ -1654,10 +1707,14 @@ static void choose_service_tree(struct cfq_data *cfqd, struct cfq_group *cfqg)
static struct cfq_group *cfq_get_next_cfqg(struct cfq_data *cfqd)
{
struct cfq_rb_root *st = &cfqd->grp_service_tree;
+ struct cfq_group *cfqg;
if (RB_EMPTY_ROOT(&st->rb))
return NULL;
- return cfq_rb_first_group(st);
+ cfqg = cfq_rb_first_group(st);
+ st->active = &cfqg->rb_node;
+ update_min_vdisktime(st);
+ return cfqg;
}
static void cfq_choose_cfqg(struct cfq_data *cfqd)
@@ -3150,6 +3207,9 @@ static void *cfq_init_queue(struct request_queue *q)
*st = CFQ_RB_ROOT;
RB_CLEAR_NODE(&cfqg->rb_node);
+ /* Give preference to root group over other groups */
+ cfqg->weight = 2*BLKIO_WEIGHT_DEFAULT;
+
/*
* Not strictly needed (since RB_ROOT just clears the node and we
* zeroed cfqd on alloc), but better be safe in case someone decides
OpenPOWER on IntegriCloud