kernel_optimize_test/block/blk-rq-qos.h
Dennis Zhou 13369816cb block: fix blk-iolatency accounting underflow
The blk-iolatency controller measures the time from rq_qos_throttle() to
rq_qos_done_bio() and attributes this time to the first bio that needs
to create the request. This means if a bio is plug-mergeable or
bio-mergeable, it gets to bypass the blk-iolatency controller.

The recent series [1], to tag all bios w/ blkgs undermined how iolatency
was determining which bios it was charging and should process in
rq_qos_done_bio(). Because all bios are being tagged, this caused the
atomic_t for the struct rq_wait inflight count to underflow and result
in a stall.

This patch adds a new flag BIO_TRACKED to let controllers know that a
bio is going through the rq_qos path. blk-iolatency now checks if this
flag is set to see if it should process the bio in rq_qos_done_bio().

Overloading BLK_QUEUE_ENTERED works, but makes the flag rules confusing.
BIO_THROTTLED was another candidate, but the flag is set for all bios
that have gone through blk-throttle code. Overloading a flag comes with
the burden of making sure that when either implementation changes, a
change in setting rules for one doesn't cause a bug in the other. So
here, we unfortunately opt for adding a new flag.

[1] https://lore.kernel.org/lkml/20181205171039.73066-1-dennis@kernel.org/

Fixes: 5cdf2e3fea ("blkcg: associate blkg when associating a device")
Signed-off-by: Dennis Zhou <dennis@kernel.org>
Cc: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-12-17 11:19:54 -07:00

190 lines
4.4 KiB
C

#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_CGROUP,
};
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 (*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 (*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_CGROUP);
}
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_CGROUP:
return "cgroup";
}
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_done_bio(struct rq_qos *rqos, struct bio *bio);
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);
}
void rq_qos_exit(struct request_queue *);
#endif