forked from luck/tmp_suning_uos_patched
7caa47151a
This patchset implements IO cost model based work-conserving
proportional controller.
While io.latency provides the capability to comprehensively prioritize
and protect IOs depending on the cgroups, its protection is binary -
the lowest latency target cgroup which is suffering is protected at
the cost of all others. In many use cases including stacking multiple
workload containers in a single system, it's necessary to distribute
IO capacity with better granularity.
One challenge of controlling IO resources is the lack of trivially
observable cost metric. The most common metrics - bandwidth and iops
- can be off by orders of magnitude depending on the device type and
IO pattern. However, the cost isn't a complete mystery. Given
several key attributes, we can make fairly reliable predictions on how
expensive a given stream of IOs would be, at least compared to other
IO patterns.
The function which determines the cost of a given IO is the IO cost
model for the device. This controller distributes IO capacity based
on the costs estimated by such model. The more accurate the cost
model the better but the controller adapts based on IO completion
latency and as long as the relative costs across differents IO
patterns are consistent and sensible, it'll adapt to the actual
performance of the device.
Currently, the only implemented cost model is a simple linear one with
a few sets of default parameters for different classes of device.
This covers most common devices reasonably well. All the
infrastructure to tune and add different cost models is already in
place and a later patch will also allow using bpf progs for cost
models.
Please see the top comment in blk-iocost.c and documentation for
more details.
v2: Rebased on top of RQ_ALLOC_TIME changes and folded in Rik's fix
for a divide-by-zero bug in current_hweight() triggered by zero
inuse_sum.
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Andy Newell <newella@fb.com>
Cc: Josef Bacik <jbacik@fb.com>
Cc: Rik van Riel <riel@surriel.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
211 lines
5.0 KiB
C
211 lines
5.0 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef RQ_QOS_H
|
|
#define RQ_QOS_H
|
|
|
|
#include <linux/kernel.h>
|
|
#include <linux/blkdev.h>
|
|
#include <linux/blk_types.h>
|
|
#include <linux/atomic.h>
|
|
#include <linux/wait.h>
|
|
|
|
#include "blk-mq-debugfs.h"
|
|
|
|
struct blk_mq_debugfs_attr;
|
|
|
|
enum rq_qos_id {
|
|
RQ_QOS_WBT,
|
|
RQ_QOS_LATENCY,
|
|
RQ_QOS_COST,
|
|
};
|
|
|
|
struct rq_wait {
|
|
wait_queue_head_t wait;
|
|
atomic_t inflight;
|
|
};
|
|
|
|
struct rq_qos {
|
|
struct rq_qos_ops *ops;
|
|
struct request_queue *q;
|
|
enum rq_qos_id id;
|
|
struct rq_qos *next;
|
|
#ifdef CONFIG_BLK_DEBUG_FS
|
|
struct dentry *debugfs_dir;
|
|
#endif
|
|
};
|
|
|
|
struct rq_qos_ops {
|
|
void (*throttle)(struct rq_qos *, struct bio *);
|
|
void (*track)(struct rq_qos *, struct request *, struct bio *);
|
|
void (*merge)(struct rq_qos *, struct request *, struct bio *);
|
|
void (*issue)(struct rq_qos *, struct request *);
|
|
void (*requeue)(struct rq_qos *, struct request *);
|
|
void (*done)(struct rq_qos *, struct request *);
|
|
void (*done_bio)(struct rq_qos *, struct bio *);
|
|
void (*cleanup)(struct rq_qos *, struct bio *);
|
|
void (*queue_depth_changed)(struct rq_qos *);
|
|
void (*exit)(struct rq_qos *);
|
|
const struct blk_mq_debugfs_attr *debugfs_attrs;
|
|
};
|
|
|
|
struct rq_depth {
|
|
unsigned int max_depth;
|
|
|
|
int scale_step;
|
|
bool scaled_max;
|
|
|
|
unsigned int queue_depth;
|
|
unsigned int default_depth;
|
|
};
|
|
|
|
static inline struct rq_qos *rq_qos_id(struct request_queue *q,
|
|
enum rq_qos_id id)
|
|
{
|
|
struct rq_qos *rqos;
|
|
for (rqos = q->rq_qos; rqos; rqos = rqos->next) {
|
|
if (rqos->id == id)
|
|
break;
|
|
}
|
|
return rqos;
|
|
}
|
|
|
|
static inline struct rq_qos *wbt_rq_qos(struct request_queue *q)
|
|
{
|
|
return rq_qos_id(q, RQ_QOS_WBT);
|
|
}
|
|
|
|
static inline struct rq_qos *blkcg_rq_qos(struct request_queue *q)
|
|
{
|
|
return rq_qos_id(q, RQ_QOS_LATENCY);
|
|
}
|
|
|
|
static inline const char *rq_qos_id_to_name(enum rq_qos_id id)
|
|
{
|
|
switch (id) {
|
|
case RQ_QOS_WBT:
|
|
return "wbt";
|
|
case RQ_QOS_LATENCY:
|
|
return "latency";
|
|
case RQ_QOS_COST:
|
|
return "cost";
|
|
}
|
|
return "unknown";
|
|
}
|
|
|
|
static inline void rq_wait_init(struct rq_wait *rq_wait)
|
|
{
|
|
atomic_set(&rq_wait->inflight, 0);
|
|
init_waitqueue_head(&rq_wait->wait);
|
|
}
|
|
|
|
static inline void rq_qos_add(struct request_queue *q, struct rq_qos *rqos)
|
|
{
|
|
rqos->next = q->rq_qos;
|
|
q->rq_qos = rqos;
|
|
|
|
if (rqos->ops->debugfs_attrs)
|
|
blk_mq_debugfs_register_rqos(rqos);
|
|
}
|
|
|
|
static inline void rq_qos_del(struct request_queue *q, struct rq_qos *rqos)
|
|
{
|
|
struct rq_qos *cur, *prev = NULL;
|
|
for (cur = q->rq_qos; cur; cur = cur->next) {
|
|
if (cur == rqos) {
|
|
if (prev)
|
|
prev->next = rqos->next;
|
|
else
|
|
q->rq_qos = cur;
|
|
break;
|
|
}
|
|
prev = cur;
|
|
}
|
|
|
|
blk_mq_debugfs_unregister_rqos(rqos);
|
|
}
|
|
|
|
typedef bool (acquire_inflight_cb_t)(struct rq_wait *rqw, void *private_data);
|
|
typedef void (cleanup_cb_t)(struct rq_wait *rqw, void *private_data);
|
|
|
|
void rq_qos_wait(struct rq_wait *rqw, void *private_data,
|
|
acquire_inflight_cb_t *acquire_inflight_cb,
|
|
cleanup_cb_t *cleanup_cb);
|
|
bool rq_wait_inc_below(struct rq_wait *rq_wait, unsigned int limit);
|
|
void rq_depth_scale_up(struct rq_depth *rqd);
|
|
void rq_depth_scale_down(struct rq_depth *rqd, bool hard_throttle);
|
|
bool rq_depth_calc_max_depth(struct rq_depth *rqd);
|
|
|
|
void __rq_qos_cleanup(struct rq_qos *rqos, struct bio *bio);
|
|
void __rq_qos_done(struct rq_qos *rqos, struct request *rq);
|
|
void __rq_qos_issue(struct rq_qos *rqos, struct request *rq);
|
|
void __rq_qos_requeue(struct rq_qos *rqos, struct request *rq);
|
|
void __rq_qos_throttle(struct rq_qos *rqos, struct bio *bio);
|
|
void __rq_qos_track(struct rq_qos *rqos, struct request *rq, struct bio *bio);
|
|
void __rq_qos_merge(struct rq_qos *rqos, struct request *rq, struct bio *bio);
|
|
void __rq_qos_done_bio(struct rq_qos *rqos, struct bio *bio);
|
|
void __rq_qos_queue_depth_changed(struct rq_qos *rqos);
|
|
|
|
static inline void rq_qos_cleanup(struct request_queue *q, struct bio *bio)
|
|
{
|
|
if (q->rq_qos)
|
|
__rq_qos_cleanup(q->rq_qos, bio);
|
|
}
|
|
|
|
static inline void rq_qos_done(struct request_queue *q, struct request *rq)
|
|
{
|
|
if (q->rq_qos)
|
|
__rq_qos_done(q->rq_qos, rq);
|
|
}
|
|
|
|
static inline void rq_qos_issue(struct request_queue *q, struct request *rq)
|
|
{
|
|
if (q->rq_qos)
|
|
__rq_qos_issue(q->rq_qos, rq);
|
|
}
|
|
|
|
static inline void rq_qos_requeue(struct request_queue *q, struct request *rq)
|
|
{
|
|
if (q->rq_qos)
|
|
__rq_qos_requeue(q->rq_qos, rq);
|
|
}
|
|
|
|
static inline void rq_qos_done_bio(struct request_queue *q, struct bio *bio)
|
|
{
|
|
if (q->rq_qos)
|
|
__rq_qos_done_bio(q->rq_qos, bio);
|
|
}
|
|
|
|
static inline void rq_qos_throttle(struct request_queue *q, struct bio *bio)
|
|
{
|
|
/*
|
|
* BIO_TRACKED lets controllers know that a bio went through the
|
|
* normal rq_qos path.
|
|
*/
|
|
bio_set_flag(bio, BIO_TRACKED);
|
|
if (q->rq_qos)
|
|
__rq_qos_throttle(q->rq_qos, bio);
|
|
}
|
|
|
|
static inline void rq_qos_track(struct request_queue *q, struct request *rq,
|
|
struct bio *bio)
|
|
{
|
|
if (q->rq_qos)
|
|
__rq_qos_track(q->rq_qos, rq, bio);
|
|
}
|
|
|
|
static inline void rq_qos_merge(struct request_queue *q, struct request *rq,
|
|
struct bio *bio)
|
|
{
|
|
if (q->rq_qos)
|
|
__rq_qos_merge(q->rq_qos, rq, bio);
|
|
}
|
|
|
|
static inline void rq_qos_queue_depth_changed(struct request_queue *q)
|
|
{
|
|
if (q->rq_qos)
|
|
__rq_qos_queue_depth_changed(q->rq_qos);
|
|
}
|
|
|
|
void rq_qos_exit(struct request_queue *);
|
|
|
|
#endif
|