From e34cbd307477ae07c5d8a8d0bd15e65a9ddaba5c Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 9 Nov 2016 12:36:15 -0700 Subject: 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 --- block/blk-wbt.h | 165 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 165 insertions(+) create mode 100644 block/blk-wbt.h (limited to 'block/blk-wbt.h') diff --git a/block/blk-wbt.h b/block/blk-wbt.h new file mode 100644 index 0000000000000..e57700337c265 --- /dev/null +++ b/block/blk-wbt.h @@ -0,0 +1,165 @@ +#ifndef WB_THROTTLE_H +#define WB_THROTTLE_H + +#include +#include +#include +#include +#include + +#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; + struct backing_dev_info *bdi; + 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; +} + +struct backing_dev_info; + +#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 -- cgit v1.2.3