@@ -1015,6 +1015,89 @@ static int blkcg_print_stat(struct seq_file *sf, void *v)
return 0;
}
+static const char *blk_wrr_name[BLK_WRR_COUNT] = {
+ [BLK_WRR_NONE] = "none",
+ [BLK_WRR_LOW] = "low",
+ [BLK_WRR_MEDIUM] = "medium",
+ [BLK_WRR_HIGH] = "high",
+};
+
+static inline const char *blk_wrr_to_name(int wrr)
+{
+ if (wrr < BLK_WRR_NONE || wrr >= BLK_WRR_COUNT)
+ return "wrong";
+
+ return blk_wrr_name[wrr];
+}
+
+static ssize_t blkcg_wrr_write(struct kernfs_open_file *of,
+ char *buf, size_t nbytes, loff_t off)
+{
+ struct blkcg *blkcg = css_to_blkcg(of_css(of));
+ struct gendisk *disk;
+ struct request_queue *q;
+ struct blkcg_gq *blkg;
+ unsigned int major, minor;
+ int wrr, key_len, part, ret;
+ char *body;
+
+ if (sscanf(buf, "%u:%u%n", &major, &minor, &key_len) != 2)
+ return -EINVAL;
+
+ body = buf + key_len;
+ if (!isspace(*body))
+ return -EINVAL;
+ body = skip_spaces(body);
+ wrr = sysfs_match_string(blk_wrr_name, body);
+ if (wrr == BLK_WRR_COUNT)
+ return -EINVAL;
+
+ disk = get_gendisk(MKDEV(major, minor), &part);
+ if (!disk)
+ return -ENODEV;
+ if (part) {
+ ret = -EINVAL;
+ goto fail;
+ }
+
+ q = disk->queue;
+
+ blkg = blkg_lookup_create(blkcg, q);
+
+ atomic_set(&blkg->wrr, wrr);
+ put_disk_and_module(disk);
+
+ return nbytes;
+fail:
+ put_disk_and_module(disk);
+ return ret;
+}
+
+static int blkcg_wrr_show(struct seq_file *sf, void *v)
+{
+ struct blkcg *blkcg = css_to_blkcg(seq_css(sf));
+ struct blkcg_gq *blkg;
+
+ rcu_read_lock();
+
+ hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) {
+ const char *dname;
+ char *buf;
+ size_t size = seq_get_buf(sf, &buf), off = 0;
+
+ dname = blkg_dev_name(blkg);
+ if (!dname)
+ continue;
+
+ off += scnprintf(buf+off, size-off, "%s %s\n", dname,
+ blk_wrr_to_name(atomic_read(&blkg->wrr)));
+ seq_commit(sf, off);
+ }
+
+ rcu_read_unlock();
+ return 0;
+}
+
static struct cftype blkcg_files[] = {
{
.name = "stat",
@@ -1029,6 +1112,11 @@ static struct cftype blkcg_legacy_files[] = {
.name = "reset_stats",
.write_u64 = blkcg_reset_stats,
},
+ {
+ .name = "wrr",
+ .write = blkcg_wrr_write,
+ .seq_show = blkcg_wrr_show,
+ },
{ } /* terminate */
};
@@ -437,6 +437,9 @@ static const char *const hctx_types[] = {
[HCTX_TYPE_DEFAULT] = "default",
[HCTX_TYPE_READ] = "read",
[HCTX_TYPE_POLL] = "poll",
+ [HCTX_TYPE_WRR_LOW] = "wrr_low",
+ [HCTX_TYPE_WRR_MEDIUM] = "wrr_medium",
+ [HCTX_TYPE_WRR_HIGH] = "wrr_high",
};
static int hctx_type_show(void *data, struct seq_file *m)
@@ -7,6 +7,7 @@
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/blk-mq.h>
+#include <linux/blk-cgroup.h>
#include <trace/events/block.h>
@@ -322,10 +323,13 @@ bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio)
{
struct elevator_queue *e = q->elevator;
struct blk_mq_ctx *ctx = blk_mq_get_ctx(q);
- struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, bio->bi_opf, ctx);
+ struct blk_mq_hw_ctx *hctx;
+ struct blkcg_gq *blkg = bio->bi_blkg;
+ int wrr = blkg ? atomic_read(&blkg->wrr) : BLK_WRR_NONE;
bool ret = false;
enum hctx_type type;
+ hctx = blk_mq_map_queue(q, bio->bi_opf, ctx, wrr);
if (e && e->type->ops.bio_merge) {
blk_mq_put_ctx(ctx);
return e->type->ops.bio_merge(hctx, bio);
@@ -106,7 +106,7 @@ static int __blk_mq_get_tag(struct blk_mq_alloc_data *data,
return __sbitmap_queue_get(bt);
}
-unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data)
+unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data, int wrr)
{
struct blk_mq_tags *tags = blk_mq_tags_from_data(data);
struct sbitmap_queue *bt;
@@ -171,7 +171,7 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data)
data->ctx = blk_mq_get_ctx(data->q);
data->hctx = blk_mq_map_queue(data->q, data->cmd_flags,
- data->ctx);
+ data->ctx, wrr);
tags = blk_mq_tags_from_data(data);
if (data->flags & BLK_MQ_REQ_RESERVED)
bt = &tags->breserved_tags;
@@ -25,7 +25,7 @@ struct blk_mq_tags {
extern struct blk_mq_tags *blk_mq_init_tags(unsigned int nr_tags, unsigned int reserved_tags, int node, int alloc_policy);
extern void blk_mq_free_tags(struct blk_mq_tags *tags);
-extern unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data);
+extern unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data, int wrr);
extern void blk_mq_put_tag(struct blk_mq_hw_ctx *hctx, struct blk_mq_tags *tags,
struct blk_mq_ctx *ctx, unsigned int tag);
extern bool blk_mq_has_free_tags(struct blk_mq_tags *tags);
@@ -356,6 +356,12 @@ static struct request *blk_mq_get_request(struct request_queue *q,
struct request *rq;
unsigned int tag;
bool put_ctx_on_error = false;
+ int wrr;
+
+ if (bio && bio->bi_blkg)
+ wrr = atomic_read(&bio->bi_blkg->wrr);
+ else
+ wrr = BLK_WRR_NONE;
blk_queue_enter_live(q);
data->q = q;
@@ -365,7 +371,7 @@ static struct request *blk_mq_get_request(struct request_queue *q,
}
if (likely(!data->hctx))
data->hctx = blk_mq_map_queue(q, data->cmd_flags,
- data->ctx);
+ data->ctx, wrr);
if (data->cmd_flags & REQ_NOWAIT)
data->flags |= BLK_MQ_REQ_NOWAIT;
@@ -385,7 +391,7 @@ static struct request *blk_mq_get_request(struct request_queue *q,
blk_mq_tag_busy(data->hctx);
}
- tag = blk_mq_get_tag(data);
+ tag = blk_mq_get_tag(data, wrr);
if (tag == BLK_MQ_TAG_FAIL) {
if (put_ctx_on_error) {
blk_mq_put_ctx(data->ctx);
@@ -1060,7 +1066,7 @@ bool blk_mq_get_driver_tag(struct request *rq)
data.flags |= BLK_MQ_REQ_RESERVED;
shared = blk_mq_tag_busy(data.hctx);
- rq->tag = blk_mq_get_tag(&data);
+ rq->tag = blk_mq_get_tag(&data, BLK_WRR_NONE);
if (rq->tag >= 0) {
if (shared) {
rq->rq_flags |= RQF_MQ_INFLIGHT;
@@ -101,7 +101,8 @@ static inline struct blk_mq_hw_ctx *blk_mq_map_queue_type(struct request_queue *
*/
static inline struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q,
unsigned int flags,
- struct blk_mq_ctx *ctx)
+ struct blk_mq_ctx *ctx,
+ int wrr)
{
enum hctx_type type = HCTX_TYPE_DEFAULT;
@@ -110,7 +111,19 @@ static inline struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q,
*/
if (flags & REQ_HIPRI)
type = HCTX_TYPE_POLL;
- else if ((flags & REQ_OP_MASK) == REQ_OP_READ)
+ else if (wrr > BLK_WRR_NONE && wrr < BLK_WRR_COUNT) {
+ switch (wrr) {
+ case BLK_WRR_LOW:
+ type = HCTX_TYPE_WRR_LOW;
+ break;
+ case BLK_WRR_MEDIUM:
+ type = HCTX_TYPE_WRR_MEDIUM;
+ break;
+ default:
+ type = HCTX_TYPE_WRR_HIGH;
+ break;
+ }
+ } else if ((flags & REQ_OP_MASK) == REQ_OP_READ)
type = HCTX_TYPE_READ;
return ctx->hctxs[type];
@@ -38,7 +38,7 @@ extern struct ida blk_queue_ida;
static inline struct blk_flush_queue *
blk_get_flush_queue(struct request_queue *q, struct blk_mq_ctx *ctx)
{
- return blk_mq_map_queue(q, REQ_OP_FLUSH, ctx)->fq;
+ return blk_mq_map_queue(q, REQ_OP_FLUSH, ctx, BLK_WRR_NONE)->fq;
}
static inline void __blk_get_queue(struct request_queue *q)
@@ -141,6 +141,8 @@ struct blkcg_gq {
atomic64_t delay_start;
u64 last_delay;
int last_use;
+ /* weighted round robin */
+ atomic_t wrr;
};
typedef struct blkcg_policy_data *(blkcg_pol_alloc_cpd_fn)(gfp_t gfp);
@@ -86,10 +86,22 @@ enum hctx_type {
HCTX_TYPE_DEFAULT, /* all I/O not otherwise accounted for */
HCTX_TYPE_READ, /* just for READ I/O */
HCTX_TYPE_POLL, /* polled I/O of any kind */
+ HCTX_TYPE_WRR_LOW, /* blkcg: weighted round robin - low */
+ HCTX_TYPE_WRR_MEDIUM, /* blkcg: weighted round robin - medium */
+ HCTX_TYPE_WRR_HIGH, /* blkcg: weighted round robin - high */
HCTX_MAX_TYPES,
};
+enum blk_wrr {
+ BLK_WRR_NONE,
+ BLK_WRR_LOW,
+ BLK_WRR_MEDIUM,
+ BLK_WRR_HIGH,
+
+ BLK_WRR_COUNT,
+};
+
struct blk_mq_tag_set {
/*
* map[] holds ctx -> hctx mappings, one map exists for each type
Each block cgroup can select a weighted round robin type to make its io requests go to the specified haredware queue. Now we support three round robin type high, medium, low like what nvme specification donse. Signed-off-by: Weiping Zhang <zhangweiping@didiglobal.com> --- block/blk-cgroup.c | 88 ++++++++++++++++++++++++++++++++++++++++++++++ block/blk-mq-debugfs.c | 3 ++ block/blk-mq-sched.c | 6 +++- block/blk-mq-tag.c | 4 +-- block/blk-mq-tag.h | 2 +- block/blk-mq.c | 12 +++++-- block/blk-mq.h | 17 +++++++-- block/blk.h | 2 +- include/linux/blk-cgroup.h | 2 ++ include/linux/blk-mq.h | 12 +++++++ 10 files changed, 138 insertions(+), 10 deletions(-)