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>

block/Makefile

@@ -24,3 +24,4 @@ obj-$(CONFIG_BLK_CMDLINE_PARSER)	+= cmdline-parser.o
 obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o blk-integrity.o t10-pi.o
 obj-$(CONFIG_BLK_MQ_PCI)	+= blk-mq-pci.o
 obj-$(CONFIG_BLK_DEV_ZONED)	+= blk-zoned.o
+obj-$(CONFIG_BLK_WBT)		+= blk-wbt.o

block/blk-wbt.h

@@ -0,0 +1,165 @@
+#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;
+	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

include/trace/events/wbt.h

@@ -0,0 +1,153 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM wbt
+
+#if !defined(_TRACE_WBT_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_WBT_H
+
+#include <linux/tracepoint.h>
+#include "../../../block/blk-wbt.h"
+
+/**
+ * wbt_stat - trace stats for blk_wb
+ * @stat: array of read/write stats
+ */
+TRACE_EVENT(wbt_stat,
+
+	TP_PROTO(struct backing_dev_info *bdi, struct blk_rq_stat *stat),
+
+	TP_ARGS(bdi, stat),
+
+	TP_STRUCT__entry(
+		__array(char, name, 32)
+		__field(s64, rmean)
+		__field(u64, rmin)
+		__field(u64, rmax)
+		__field(s64, rnr_samples)
+		__field(s64, rtime)
+		__field(s64, wmean)
+		__field(u64, wmin)
+		__field(u64, wmax)
+		__field(s64, wnr_samples)
+		__field(s64, wtime)
+	),
+
+	TP_fast_assign(
+		strncpy(__entry->name, dev_name(bdi->dev), 32);
+		__entry->rmean		= stat[0].mean;
+		__entry->rmin		= stat[0].min;
+		__entry->rmax		= stat[0].max;
+		__entry->rnr_samples	= stat[0].nr_samples;
+		__entry->wmean		= stat[1].mean;
+		__entry->wmin		= stat[1].min;
+		__entry->wmax		= stat[1].max;
+		__entry->wnr_samples	= stat[1].nr_samples;
+	),
+
+	TP_printk("%s: rmean=%llu, rmin=%llu, rmax=%llu, rsamples=%llu, "
+		  "wmean=%llu, wmin=%llu, wmax=%llu, wsamples=%llu\n",
+		  __entry->name, __entry->rmean, __entry->rmin, __entry->rmax,
+		  __entry->rnr_samples, __entry->wmean, __entry->wmin,
+		  __entry->wmax, __entry->wnr_samples)
+);
+
+/**
+ * wbt_lat - trace latency event
+ * @lat: latency trigger
+ */
+TRACE_EVENT(wbt_lat,
+
+	TP_PROTO(struct backing_dev_info *bdi, unsigned long lat),
+
+	TP_ARGS(bdi, lat),
+
+	TP_STRUCT__entry(
+		__array(char, name, 32)
+		__field(unsigned long, lat)
+	),
+
+	TP_fast_assign(
+		strncpy(__entry->name, dev_name(bdi->dev), 32);
+		__entry->lat = div_u64(lat, 1000);
+	),
+
+	TP_printk("%s: latency %lluus\n", __entry->name,
+			(unsigned long long) __entry->lat)
+);
+
+/**
+ * wbt_step - trace wb event step
+ * @msg: context message
+ * @step: the current scale step count
+ * @window: the current monitoring window
+ * @bg: the current background queue limit
+ * @normal: the current normal writeback limit
+ * @max: the current max throughput writeback limit
+ */
+TRACE_EVENT(wbt_step,
+
+	TP_PROTO(struct backing_dev_info *bdi, const char *msg,
+		 int step, unsigned long window, unsigned int bg,
+		 unsigned int normal, unsigned int max),
+
+	TP_ARGS(bdi, msg, step, window, bg, normal, max),
+
+	TP_STRUCT__entry(
+		__array(char, name, 32)
+		__field(const char *, msg)
+		__field(int, step)
+		__field(unsigned long, window)
+		__field(unsigned int, bg)
+		__field(unsigned int, normal)
+		__field(unsigned int, max)
+	),
+
+	TP_fast_assign(
+		strncpy(__entry->name, dev_name(bdi->dev), 32);
+		__entry->msg	= msg;
+		__entry->step	= step;
+		__entry->window	= div_u64(window, 1000);
+		__entry->bg	= bg;
+		__entry->normal	= normal;
+		__entry->max	= max;
+	),
+
+	TP_printk("%s: %s: step=%d, window=%luus, background=%u, normal=%u, max=%u\n",
+		  __entry->name, __entry->msg, __entry->step, __entry->window,
+		  __entry->bg, __entry->normal, __entry->max)
+);
+
+/**
+ * wbt_timer - trace wb timer event
+ * @status: timer state status
+ * @step: the current scale step count
+ * @inflight: tracked writes inflight
+ */
+TRACE_EVENT(wbt_timer,
+
+	TP_PROTO(struct backing_dev_info *bdi, unsigned int status,
+		 int step, unsigned int inflight),
+
+	TP_ARGS(bdi, status, step, inflight),
+
+	TP_STRUCT__entry(
+		__array(char, name, 32)
+		__field(unsigned int, status)
+		__field(int, step)
+		__field(unsigned int, inflight)
+	),
+
+	TP_fast_assign(
+		strncpy(__entry->name, dev_name(bdi->dev), 32);
+		__entry->status		= status;
+		__entry->step		= step;
+		__entry->inflight	= inflight;
+	),
+
+	TP_printk("%s: status=%u, step=%d, inflight=%u\n", __entry->name,
+		  __entry->status, __entry->step, __entry->inflight)
+);
+
+#endif /* _TRACE_WBT_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>