blk-wbt: add general throttling mechanism
We can hook this up to the block layer, to help throttle buffered
writes.
wbt registers a few trace points that can be used to track what is
happening in the system:
wbt_lat: 259:0: latency 2446318
wbt_stat: 259:0: rmean=2446318, rmin=2446318, rmax=2446318, rsamples=1,
wmean=518866, wmin=15522, wmax=5330353, wsamples=57
wbt_step: 259:0: step down: step=1, window=72727272, background=8, normal=16, max=32
This shows a sync issue event (wbt_lat) that exceeded it's time. wbt_stat
dumps the current read/write stats for that window, and wbt_step shows a
step down event where we now scale back writes. Each trace includes the
device, 259:0 in this case.
Signed-off-by: Jens Axboe <axboe@fb.com>
2016-11-10 03:36:15 +08:00
|
|
|
#ifndef WB_THROTTLE_H
|
|
|
|
#define WB_THROTTLE_H
|
|
|
|
|
|
|
|
#include <linux/kernel.h>
|
|
|
|
#include <linux/atomic.h>
|
|
|
|
#include <linux/wait.h>
|
|
|
|
#include <linux/timer.h>
|
|
|
|
#include <linux/ktime.h>
|
|
|
|
|
|
|
|
#include "blk-stat.h"
|
|
|
|
|
|
|
|
enum wbt_flags {
|
|
|
|
WBT_TRACKED = 1, /* write, tracked for throttling */
|
|
|
|
WBT_READ = 2, /* read */
|
|
|
|
WBT_KSWAPD = 4, /* write, from kswapd */
|
|
|
|
|
|
|
|
WBT_NR_BITS = 3, /* number of bits */
|
|
|
|
};
|
|
|
|
|
|
|
|
enum {
|
|
|
|
WBT_NUM_RWQ = 2,
|
|
|
|
};
|
|
|
|
|
|
|
|
static inline void wbt_clear_state(struct blk_issue_stat *stat)
|
|
|
|
{
|
|
|
|
stat->time &= BLK_STAT_TIME_MASK;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline enum wbt_flags wbt_stat_to_mask(struct blk_issue_stat *stat)
|
|
|
|
{
|
|
|
|
return (stat->time & BLK_STAT_MASK) >> BLK_STAT_SHIFT;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void wbt_track(struct blk_issue_stat *stat, enum wbt_flags wb_acct)
|
|
|
|
{
|
|
|
|
stat->time |= ((u64) wb_acct) << BLK_STAT_SHIFT;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline bool wbt_is_tracked(struct blk_issue_stat *stat)
|
|
|
|
{
|
|
|
|
return (stat->time >> BLK_STAT_SHIFT) & WBT_TRACKED;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline bool wbt_is_read(struct blk_issue_stat *stat)
|
|
|
|
{
|
|
|
|
return (stat->time >> BLK_STAT_SHIFT) & WBT_READ;
|
|
|
|
}
|
|
|
|
|
|
|
|
struct wb_stat_ops {
|
|
|
|
void (*get)(void *, struct blk_rq_stat *);
|
|
|
|
bool (*is_current)(struct blk_rq_stat *);
|
|
|
|
void (*clear)(void *);
|
|
|
|
};
|
|
|
|
|
|
|
|
struct rq_wait {
|
|
|
|
wait_queue_head_t wait;
|
|
|
|
atomic_t inflight;
|
|
|
|
};
|
|
|
|
|
|
|
|
struct rq_wb {
|
|
|
|
/*
|
|
|
|
* Settings that govern how we throttle
|
|
|
|
*/
|
|
|
|
unsigned int wb_background; /* background writeback */
|
|
|
|
unsigned int wb_normal; /* normal writeback */
|
|
|
|
unsigned int wb_max; /* max throughput writeback */
|
|
|
|
int scale_step;
|
|
|
|
bool scaled_max;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Number of consecutive periods where we don't have enough
|
|
|
|
* information to make a firm scale up/down decision.
|
|
|
|
*/
|
|
|
|
unsigned int unknown_cnt;
|
|
|
|
|
|
|
|
u64 win_nsec; /* default window size */
|
|
|
|
u64 cur_win_nsec; /* current window size */
|
|
|
|
|
|
|
|
struct timer_list window_timer;
|
|
|
|
|
|
|
|
s64 sync_issue;
|
|
|
|
void *sync_cookie;
|
|
|
|
|
|
|
|
unsigned int wc;
|
|
|
|
unsigned int queue_depth;
|
|
|
|
|
|
|
|
unsigned long last_issue; /* last non-throttled issue */
|
|
|
|
unsigned long last_comp; /* last non-throttled comp */
|
|
|
|
unsigned long min_lat_nsec;
|
2016-11-11 12:52:53 +08:00
|
|
|
struct request_queue *queue;
|
blk-wbt: add general throttling mechanism
We can hook this up to the block layer, to help throttle buffered
writes.
wbt registers a few trace points that can be used to track what is
happening in the system:
wbt_lat: 259:0: latency 2446318
wbt_stat: 259:0: rmean=2446318, rmin=2446318, rmax=2446318, rsamples=1,
wmean=518866, wmin=15522, wmax=5330353, wsamples=57
wbt_step: 259:0: step down: step=1, window=72727272, background=8, normal=16, max=32
This shows a sync issue event (wbt_lat) that exceeded it's time. wbt_stat
dumps the current read/write stats for that window, and wbt_step shows a
step down event where we now scale back writes. Each trace includes the
device, 259:0 in this case.
Signed-off-by: Jens Axboe <axboe@fb.com>
2016-11-10 03:36:15 +08:00
|
|
|
struct rq_wait rq_wait[WBT_NUM_RWQ];
|
|
|
|
|
|
|
|
struct wb_stat_ops *stat_ops;
|
|
|
|
void *ops_data;
|
|
|
|
};
|
|
|
|
|
|
|
|
static inline unsigned int wbt_inflight(struct rq_wb *rwb)
|
|
|
|
{
|
|
|
|
unsigned int i, ret = 0;
|
|
|
|
|
|
|
|
for (i = 0; i < WBT_NUM_RWQ; i++)
|
|
|
|
ret += atomic_read(&rwb->rq_wait[i].inflight);
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
#ifdef CONFIG_BLK_WBT
|
|
|
|
|
|
|
|
void __wbt_done(struct rq_wb *, enum wbt_flags);
|
|
|
|
void wbt_done(struct rq_wb *, struct blk_issue_stat *);
|
|
|
|
enum wbt_flags wbt_wait(struct rq_wb *, struct bio *, spinlock_t *);
|
|
|
|
int wbt_init(struct request_queue *, struct wb_stat_ops *);
|
|
|
|
void wbt_exit(struct request_queue *);
|
|
|
|
void wbt_update_limits(struct rq_wb *);
|
|
|
|
void wbt_requeue(struct rq_wb *, struct blk_issue_stat *);
|
|
|
|
void wbt_issue(struct rq_wb *, struct blk_issue_stat *);
|
|
|
|
void wbt_disable(struct rq_wb *);
|
|
|
|
|
|
|
|
void wbt_set_queue_depth(struct rq_wb *, unsigned int);
|
|
|
|
void wbt_set_write_cache(struct rq_wb *, bool);
|
|
|
|
|
|
|
|
#else
|
|
|
|
|
|
|
|
static inline void __wbt_done(struct rq_wb *rwb, enum wbt_flags flags)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
static inline void wbt_done(struct rq_wb *rwb, struct blk_issue_stat *stat)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
static inline enum wbt_flags wbt_wait(struct rq_wb *rwb, struct bio *bio,
|
|
|
|
spinlock_t *lock)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
static inline int wbt_init(struct request_queue *q, struct wb_stat_ops *ops)
|
|
|
|
{
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
static inline void wbt_exit(struct request_queue *q)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
static inline void wbt_update_limits(struct rq_wb *rwb)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
static inline void wbt_requeue(struct rq_wb *rwb, struct blk_issue_stat *stat)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
static inline void wbt_issue(struct rq_wb *rwb, struct blk_issue_stat *stat)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
static inline void wbt_disable(struct rq_wb *rwb)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
static inline void wbt_set_queue_depth(struct rq_wb *rwb, unsigned int depth)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
static inline void wbt_set_write_cache(struct rq_wb *rwb, bool wc)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
|
|
|
#endif /* CONFIG_BLK_WBT */
|
|
|
|
|
|
|
|
#endif
|