5 * SOME HIGH LEVEL CODE DOCUMENTATION:
7 * Bcache mostly works with cache sets, cache devices, and backing devices.
9 * Support for multiple cache devices hasn't quite been finished off yet, but
10 * it's about 95% plumbed through. A cache set and its cache devices is sort of
11 * like a md raid array and its component devices. Most of the code doesn't care
12 * about individual cache devices, the main abstraction is the cache set.
14 * Multiple cache devices is intended to give us the ability to mirror dirty
15 * cached data and metadata, without mirroring clean cached data.
17 * Backing devices are different, in that they have a lifetime independent of a
18 * cache set. When you register a newly formatted backing device it'll come up
19 * in passthrough mode, and then you can attach and detach a backing device from
20 * a cache set at runtime - while it's mounted and in use. Detaching implicitly
21 * invalidates any cached data for that backing device.
23 * A cache set can have multiple (many) backing devices attached to it.
25 * There's also flash only volumes - this is the reason for the distinction
26 * between struct cached_dev and struct bcache_device. A flash only volume
27 * works much like a bcache device that has a backing device, except the
28 * "cached" data is always dirty. The end result is that we get thin
29 * provisioning with very little additional code.
31 * Flash only volumes work but they're not production ready because the moving
32 * garbage collector needs more work. More on that later.
36 * Bcache is primarily designed for caching, which means that in normal
37 * operation all of our available space will be allocated. Thus, we need an
38 * efficient way of deleting things from the cache so we can write new things to
41 * To do this, we first divide the cache device up into buckets. A bucket is the
42 * unit of allocation; they're typically around 1 mb - anywhere from 128k to 2M+
45 * Each bucket has a 16 bit priority, and an 8 bit generation associated with
46 * it. The gens and priorities for all the buckets are stored contiguously and
47 * packed on disk (in a linked list of buckets - aside from the superblock, all
48 * of bcache's metadata is stored in buckets).
50 * The priority is used to implement an LRU. We reset a bucket's priority when
51 * we allocate it or on cache it, and every so often we decrement the priority
52 * of each bucket. It could be used to implement something more sophisticated,
53 * if anyone ever gets around to it.
55 * The generation is used for invalidating buckets. Each pointer also has an 8
56 * bit generation embedded in it; for a pointer to be considered valid, its gen
57 * must match the gen of the bucket it points into. Thus, to reuse a bucket all
58 * we have to do is increment its gen (and write its new gen to disk; we batch
61 * Bcache is entirely COW - we never write twice to a bucket, even buckets that
62 * contain metadata (including btree nodes).
66 * Bcache is in large part design around the btree.
68 * At a high level, the btree is just an index of key -> ptr tuples.
70 * Keys represent extents, and thus have a size field. Keys also have a variable
71 * number of pointers attached to them (potentially zero, which is handy for
72 * invalidating the cache).
74 * The key itself is an inode:offset pair. The inode number corresponds to a
75 * backing device or a flash only volume. The offset is the ending offset of the
76 * extent within the inode - not the starting offset; this makes lookups
77 * slightly more convenient.
79 * Pointers contain the cache device id, the offset on that device, and an 8 bit
80 * generation number. More on the gen later.
82 * Index lookups are not fully abstracted - cache lookups in particular are
83 * still somewhat mixed in with the btree code, but things are headed in that
86 * Updates are fairly well abstracted, though. There are two different ways of
87 * updating the btree; insert and replace.
89 * BTREE_INSERT will just take a list of keys and insert them into the btree -
90 * overwriting (possibly only partially) any extents they overlap with. This is
91 * used to update the index after a write.
93 * BTREE_REPLACE is really cmpxchg(); it inserts a key into the btree iff it is
94 * overwriting a key that matches another given key. This is used for inserting
95 * data into the cache after a cache miss, and for background writeback, and for
96 * the moving garbage collector.
98 * There is no "delete" operation; deleting things from the index is
99 * accomplished by either by invalidating pointers (by incrementing a bucket's
100 * gen) or by inserting a key with 0 pointers - which will overwrite anything
101 * previously present at that location in the index.
103 * This means that there are always stale/invalid keys in the btree. They're
104 * filtered out by the code that iterates through a btree node, and removed when
105 * a btree node is rewritten.
109 * Our unit of allocation is a bucket, and we we can't arbitrarily allocate and
110 * free smaller than a bucket - so, that's how big our btree nodes are.
112 * (If buckets are really big we'll only use part of the bucket for a btree node
113 * - no less than 1/4th - but a bucket still contains no more than a single
114 * btree node. I'd actually like to change this, but for now we rely on the
115 * bucket's gen for deleting btree nodes when we rewrite/split a node.)
117 * Anyways, btree nodes are big - big enough to be inefficient with a textbook
118 * btree implementation.
120 * The way this is solved is that btree nodes are internally log structured; we
121 * can append new keys to an existing btree node without rewriting it. This
122 * means each set of keys we write is sorted, but the node is not.
124 * We maintain this log structure in memory - keeping 1Mb of keys sorted would
125 * be expensive, and we have to distinguish between the keys we have written and
126 * the keys we haven't. So to do a lookup in a btree node, we have to search
127 * each sorted set. But we do merge written sets together lazily, so the cost of
128 * these extra searches is quite low (normally most of the keys in a btree node
129 * will be in one big set, and then there'll be one or two sets that are much
132 * This log structure makes bcache's btree more of a hybrid between a
133 * conventional btree and a compacting data structure, with some of the
134 * advantages of both.
136 * GARBAGE COLLECTION:
138 * We can't just invalidate any bucket - it might contain dirty data or
139 * metadata. If it once contained dirty data, other writes might overwrite it
140 * later, leaving no valid pointers into that bucket in the index.
142 * Thus, the primary purpose of garbage collection is to find buckets to reuse.
143 * It also counts how much valid data it each bucket currently contains, so that
144 * allocation can reuse buckets sooner when they've been mostly overwritten.
146 * It also does some things that are really internal to the btree
147 * implementation. If a btree node contains pointers that are stale by more than
148 * some threshold, it rewrites the btree node to avoid the bucket's generation
149 * wrapping around. It also merges adjacent btree nodes if they're empty enough.
153 * Bcache's journal is not necessary for consistency; we always strictly
154 * order metadata writes so that the btree and everything else is consistent on
155 * disk in the event of an unclean shutdown, and in fact bcache had writeback
156 * caching (with recovery from unclean shutdown) before journalling was
159 * Rather, the journal is purely a performance optimization; we can't complete a
160 * write until we've updated the index on disk, otherwise the cache would be
161 * inconsistent in the event of an unclean shutdown. This means that without the
162 * journal, on random write workloads we constantly have to update all the leaf
163 * nodes in the btree, and those writes will be mostly empty (appending at most
164 * a few keys each) - highly inefficient in terms of amount of metadata writes,
165 * and it puts more strain on the various btree resorting/compacting code.
167 * The journal is just a log of keys we've inserted; on startup we just reinsert
168 * all the keys in the open journal entries. That means that when we're updating
169 * a node in the btree, we can wait until a 4k block of keys fills up before
172 * For simplicity, we only journal updates to leaf nodes; updates to parent
173 * nodes are rare enough (since our leaf nodes are huge) that it wasn't worth
174 * the complexity to deal with journalling them (in particular, journal replay)
175 * - updates to non leaf nodes just happen synchronously (see btree_split()).
179 #define pr_fmt(fmt) "bcache: %s() " fmt "\n", __func__
181 #include <linux/bug.h>
182 #include <linux/bcache.h>
183 #include <linux/bio.h>
184 #include <linux/kobject.h>
185 #include <linux/lglock.h>
186 #include <linux/list.h>
187 #include <linux/mutex.h>
188 #include <linux/percpu-refcount.h>
189 #include <linux/radix-tree.h>
190 #include <linux/rbtree.h>
191 #include <linux/rhashtable.h>
192 #include <linux/rwsem.h>
193 #include <linux/seqlock.h>
194 #include <linux/shrinker.h>
195 #include <linux/types.h>
196 #include <linux/workqueue.h>
204 #include <linux/dynamic_fault.h>
206 #define cache_set_init_fault(name) \
207 dynamic_fault("bcache:cache_set_init:" name)
208 #define bch_meta_read_fault(name) \
209 dynamic_fault("bcache:meta:read:" name)
210 #define bch_meta_write_fault(name) \
211 dynamic_fault("bcache:meta:write:" name)
214 #define bch_fmt(_c, fmt) "bcache (%s): " fmt "\n", ((_c)->name)
217 #define bch_info(c, fmt, ...) \
218 printk(KERN_INFO bch_fmt(c, fmt), ##__VA_ARGS__)
219 #define bch_notice(c, fmt, ...) \
220 printk(KERN_NOTICE bch_fmt(c, fmt), ##__VA_ARGS__)
221 #define bch_warn(c, fmt, ...) \
222 printk(KERN_WARNING bch_fmt(c, fmt), ##__VA_ARGS__)
223 #define bch_err(c, fmt, ...) \
224 printk(KERN_ERR bch_fmt(c, fmt), ##__VA_ARGS__)
226 #define bch_verbose(c, fmt, ...) \
228 if ((c)->opts.verbose_recovery) \
229 bch_info(c, fmt, ##__VA_ARGS__); \
232 /* Parameters that are useful for debugging, but should always be compiled in: */
233 #define BCH_DEBUG_PARAMS_ALWAYS() \
234 BCH_DEBUG_PARAM(key_merging_disabled, \
235 "Disables merging of extents") \
236 BCH_DEBUG_PARAM(btree_gc_always_rewrite, \
237 "Causes mark and sweep to compact and rewrite every " \
238 "btree node it traverses") \
239 BCH_DEBUG_PARAM(btree_gc_rewrite_disabled, \
240 "Disables rewriting of btree nodes during mark and sweep")\
241 BCH_DEBUG_PARAM(btree_gc_coalesce_disabled, \
242 "Disables coalescing of btree nodes") \
243 BCH_DEBUG_PARAM(btree_shrinker_disabled, \
244 "Disables the shrinker callback for the btree node cache")
246 /* Parameters that should only be compiled in in debug mode: */
247 #define BCH_DEBUG_PARAMS_DEBUG() \
248 BCH_DEBUG_PARAM(expensive_debug_checks, \
249 "Enables various runtime debugging checks that " \
250 "significantly affect performance") \
251 BCH_DEBUG_PARAM(debug_check_bkeys, \
252 "Run bkey_debugcheck (primarily checking GC/allocation "\
253 "information) when iterating over keys") \
254 BCH_DEBUG_PARAM(version_stress_test, \
255 "Assigns random version numbers to newly written " \
256 "extents, to test overlapping extent cases") \
257 BCH_DEBUG_PARAM(verify_btree_ondisk, \
258 "Reread btree nodes at various points to verify the " \
259 "mergesort in the read path against modifications " \
262 #define BCH_DEBUG_PARAMS_ALL() BCH_DEBUG_PARAMS_ALWAYS() BCH_DEBUG_PARAMS_DEBUG()
264 #ifdef CONFIG_BCACHE_DEBUG
265 #define BCH_DEBUG_PARAMS() BCH_DEBUG_PARAMS_ALL()
267 #define BCH_DEBUG_PARAMS() BCH_DEBUG_PARAMS_ALWAYS()
270 /* name, frequency_units, duration_units */
271 #define BCH_TIME_STATS() \
272 BCH_TIME_STAT(mca_alloc, sec, us) \
273 BCH_TIME_STAT(mca_scan, sec, ms) \
274 BCH_TIME_STAT(btree_gc, sec, ms) \
275 BCH_TIME_STAT(btree_coalesce, sec, ms) \
276 BCH_TIME_STAT(btree_split, sec, us) \
277 BCH_TIME_STAT(btree_sort, ms, us) \
278 BCH_TIME_STAT(btree_read, ms, us) \
279 BCH_TIME_STAT(journal_write, us, us) \
280 BCH_TIME_STAT(journal_delay, ms, us) \
281 BCH_TIME_STAT(journal_blocked, sec, ms) \
282 BCH_TIME_STAT(journal_flush_seq, us, us)
284 #include "alloc_types.h"
285 #include "blockdev_types.h"
286 #include "buckets_types.h"
287 #include "clock_types.h"
288 #include "io_types.h"
289 #include "journal_types.h"
290 #include "keylist_types.h"
291 #include "keybuf_types.h"
292 #include "move_types.h"
293 #include "stats_types.h"
294 #include "super_types.h"
296 /* 256k, in sectors */
297 #define BTREE_NODE_SIZE_MAX 512
300 * Number of nodes we might have to allocate in a worst case btree split
301 * operation - we split all the way up to the root, then allocate a new root.
303 #define btree_reserve_required_nodes(depth) (((depth) + 1) * 2 + 1)
305 /* Number of nodes btree coalesce will try to coalesce at once */
306 #define GC_MERGE_NODES 4U
308 /* Maximum number of nodes we might need to allocate atomically: */
309 #define BTREE_RESERVE_MAX \
310 (btree_reserve_required_nodes(BTREE_MAX_DEPTH) + GC_MERGE_NODES)
312 /* Size of the freelist we allocate btree nodes from: */
313 #define BTREE_NODE_RESERVE (BTREE_RESERVE_MAX * 2)
319 GC_PHASE_PENDING_DELETE = BTREE_ID_NR + 1,
329 struct cache_member_cpu {
330 u64 nbuckets; /* device size */
331 u16 first_bucket; /* index of first bucket used */
332 u16 bucket_size; /* sectors */
343 struct cache_member_rcu {
346 struct cache_member_cpu m[];
352 CACHE_DEV_FORCE_REMOVE,
356 struct percpu_ref ref;
357 struct rcu_head free_rcu;
358 struct work_struct free_work;
359 struct work_struct remove_work;
362 struct cache_set *set;
364 struct cache_group self;
367 * Cached version of this device's member info from superblock
368 * Committed by write_super()
373 struct cache_member_cpu mi;
375 struct bcache_superblock disk_sb;
379 /* biosets used in cloned bios for replicas and moving_gc */
380 struct bio_set replica_set;
382 struct task_struct *alloc_thread;
384 struct prio_set *disk_buckets;
387 * When allocating new buckets, prio_write() gets first dibs - since we
388 * may not be allocate at all without writing priorities and gens.
389 * prio_last_buckets[] contains the last buckets we wrote priorities to
390 * (so gc can mark them as metadata).
393 u64 *prio_last_buckets;
394 spinlock_t prio_buckets_lock;
395 struct bio *bio_prio;
398 * free: Buckets that are ready to be used
400 * free_inc: Incoming buckets - these are buckets that currently have
401 * cached data in them, and we can't reuse them until after we write
402 * their new gen to disk. After prio_write() finishes writing the new
403 * gens/prios, they'll be moved to the free list (and possibly discarded
406 DECLARE_FIFO(long, free)[RESERVE_NR];
407 DECLARE_FIFO(long, free_inc);
408 spinlock_t freelist_lock;
410 size_t fifo_last_bucket;
412 /* Allocation stuff: */
414 /* most out of date gen in the btree */
416 struct bucket *buckets;
417 unsigned short bucket_bits; /* ilog2(bucket_size) */
419 /* last calculated minimum prio */
423 * Bucket book keeping. The first element is updated by GC, the
424 * second contains a saved copy of the stats from the beginning
427 struct bucket_stats_cache __percpu *bucket_stats_percpu;
428 struct bucket_stats_cache bucket_stats_cached;
430 atomic_long_t saturated_count;
431 size_t inc_gen_needs_gc;
433 struct mutex heap_lock;
434 DECLARE_HEAP(struct bucket_heap_entry, heap);
437 struct task_struct *moving_gc_read;
439 struct bch_pd_controller moving_gc_pd;
442 struct write_point tiering_write_point;
444 struct write_point copygc_write_point;
446 struct journal_device journal;
448 struct work_struct io_error_work;
450 /* The rest of this all shows up in sysfs */
451 #define IO_ERROR_SHIFT 20
455 atomic64_t meta_sectors_written;
456 atomic64_t btree_sectors_written;
457 u64 __percpu *sectors_written;
461 * Flag bits for what phase of startup/shutdown the cache set is at, how we're
462 * shutting down, etc.:
464 * CACHE_SET_UNREGISTERING means we're not just shutting down, we're detaching
465 * all the backing devices first (their cached data gets invalidated, and they
466 * won't automatically reattach).
468 * CACHE_SET_STOPPING always gets set first when we're closing down a cache set;
469 * we'll continue to run normally for awhile with CACHE_SET_STOPPING set (i.e.
470 * flushing dirty data).
472 * CACHE_SET_RUNNING means all cache devices have been registered and journal
473 * replay is complete.
477 CACHE_SET_INITIAL_GC_DONE,
481 CACHE_SET_UNREGISTERING,
484 CACHE_SET_RO_COMPLETE,
485 CACHE_SET_EMERGENCY_RO,
486 CACHE_SET_WRITE_DISABLE_COMPLETE,
487 CACHE_SET_GC_STOPPING,
488 CACHE_SET_GC_FAILURE,
489 CACHE_SET_BDEV_MOUNTED,
491 CACHE_SET_FSCK_FIXED_ERRORS,
496 struct dentry *btree;
497 struct dentry *btree_format;
498 struct dentry *failed;
504 struct list_head list;
506 struct kobject internal;
507 struct kobject opts_dir;
508 struct kobject time_stats;
509 struct completion *stop_completion;
513 struct device *chardev;
514 struct super_block *vfs_sb;
517 /* Counts outstanding writes, for clean transition to read-only */
518 struct percpu_ref writes;
519 struct work_struct read_only_work;
521 struct cache __rcu *cache[MAX_CACHES_PER_SET];
523 struct mutex mi_lock;
524 struct cache_member_rcu __rcu *members;
525 struct cache_member *disk_mi; /* protected by register_lock */
527 struct cache_set_opts opts;
530 * Cached copy in native endianness:
531 * Set by cache_sb_to_cache_set:
540 u8 meta_replicas_have;
541 u8 data_replicas_have;
546 struct cache_sb disk_sb;
547 unsigned short block_bits; /* ilog2(block_size) */
549 struct closure sb_write;
550 struct semaphore sb_write_mutex;
552 struct backing_dev_info bdi;
555 struct bio_set btree_read_bio;
557 struct btree_root btree_roots[BTREE_ID_NR];
558 struct mutex btree_root_lock;
560 bool btree_cache_table_init_done;
561 struct rhashtable btree_cache_table;
564 * We never free a struct btree, except on shutdown - we just put it on
565 * the btree_cache_freed list and reuse it later. This simplifies the
566 * code, and it doesn't cost us much memory as the memory usage is
567 * dominated by buffers that hold the actual btree node data and those
568 * can be freed - and the number of struct btrees allocated is
569 * effectively bounded.
571 * btree_cache_freeable effectively is a small cache - we use it because
572 * high order page allocations can be rather expensive, and it's quite
573 * common to delete and allocate btree nodes in quick succession. It
574 * should never grow past ~2-3 nodes in practice.
576 struct mutex btree_cache_lock;
577 struct list_head btree_cache;
578 struct list_head btree_cache_freeable;
579 struct list_head btree_cache_freed;
581 /* Number of elements in btree_cache + btree_cache_freeable lists */
582 unsigned btree_cache_used;
583 unsigned btree_cache_reserve;
584 struct shrinker btree_cache_shrink;
587 * If we need to allocate memory for a new btree node and that
588 * allocation fails, we can cannibalize another node in the btree cache
589 * to satisfy the allocation - lock to guarantee only one thread does
592 struct closure_waitlist mca_wait;
593 struct task_struct *btree_cache_alloc_lock;
595 mempool_t btree_reserve_pool;
598 * Cache of allocated btree nodes - if we allocate a btree node and
599 * don't use it, if we free it that space can't be reused until going
600 * _all_ the way through the allocator (which exposes us to a livelock
601 * when allocating btree reserves fail halfway through) - instead, we
602 * can stick them here:
605 struct open_bucket *ob;
607 } btree_reserve_cache[BTREE_NODE_RESERVE * 2];
608 unsigned btree_reserve_cache_nr;
609 struct mutex btree_reserve_cache_lock;
611 mempool_t btree_interior_update_pool;
612 struct list_head btree_interior_update_list;
613 struct mutex btree_interior_update_lock;
615 struct workqueue_struct *wq;
616 /* copygc needs its own workqueue for index updates.. */
617 struct workqueue_struct *copygc_wq;
620 struct bch_pd_controller foreground_write_pd;
621 struct delayed_work pd_controllers_update;
622 unsigned pd_controllers_update_seconds;
623 spinlock_t foreground_write_pd_lock;
624 struct bch_write_op *write_wait_head;
625 struct bch_write_op *write_wait_tail;
627 struct timer_list foreground_write_wakeup;
630 * These contain all r/w devices - i.e. devices we can currently
633 struct cache_group cache_all;
634 struct cache_group cache_tiers[CACHE_TIERS];
636 u64 capacity; /* sectors */
639 * When capacity _decreases_ (due to a disk being removed), we
640 * increment capacity_gen - this invalidates outstanding reservations
641 * and forces them to be revalidated
645 atomic64_t sectors_available;
647 struct bucket_stats_cache_set __percpu *bucket_stats_percpu;
648 struct bucket_stats_cache_set bucket_stats_cached;
649 struct lglock bucket_stats_lock;
651 struct mutex bucket_lock;
653 struct closure_waitlist freelist_wait;
657 * When we invalidate buckets, we use both the priority and the amount
658 * of good data to determine which buckets to reuse first - to weight
659 * those together consistently we keep track of the smallest nonzero
660 * priority of any bucket.
662 struct prio_clock prio_clock[2];
664 struct io_clock io_clock[2];
666 /* SECTOR ALLOCATOR */
667 struct list_head open_buckets_open;
668 struct list_head open_buckets_free;
669 unsigned open_buckets_nr_free;
670 struct closure_waitlist open_buckets_wait;
671 spinlock_t open_buckets_lock;
672 struct open_bucket open_buckets[OPEN_BUCKETS_COUNT];
674 struct write_point btree_write_point;
676 struct write_point write_points[WRITE_POINT_COUNT];
677 struct write_point promote_write_point;
680 * This write point is used for migrating data off a device
681 * and can point to any other device.
682 * We can't use the normal write points because those will
683 * gang up n replicas, and for migration we want only one new
686 struct write_point migration_write_point;
688 /* GARBAGE COLLECTION */
689 struct task_struct *gc_thread;
693 * Tracks GC's progress - everything in the range [ZERO_KEY..gc_cur_pos]
694 * has been marked by GC.
696 * gc_cur_phase is a superset of btree_ids (BTREE_ID_EXTENTS etc.)
698 * gc_cur_phase == GC_PHASE_DONE indicates that gc is finished/not
699 * currently running, and gc marks are currently valid
701 * Protected by gc_pos_lock. Only written to by GC thread, so GC thread
702 * can read without a lock.
704 seqcount_t gc_pos_lock;
705 struct gc_pos gc_pos;
708 * The allocation code needs gc_mark in struct bucket to be correct, but
709 * it's not while a gc is in progress.
711 struct rw_semaphore gc_lock;
714 struct bio_set bio_read;
715 struct bio_set bio_read_split;
716 struct bio_set bio_write;
717 struct mutex bio_bounce_pages_lock;
718 mempool_t bio_bounce_pages;
720 mempool_t lz4_workspace_pool;
721 void *zlib_workspace;
722 struct mutex zlib_workspace_lock;
723 mempool_t compression_bounce[2];
724 struct bio_decompress_worker __percpu
725 *bio_decompress_worker;
727 /* For punting bio submissions to workqueue, io.c */
728 struct bio_list bio_submit_list;
729 struct work_struct bio_submit_work;
730 spinlock_t bio_submit_lock;
732 struct bio_list read_retry_list;
733 struct work_struct read_retry_work;
734 spinlock_t read_retry_lock;
737 wait_queue_head_t writeback_wait;
738 atomic_t writeback_pages;
739 unsigned writeback_pages_max;
740 atomic_long_t nr_inodes;
743 struct task_struct *tiering_read;
744 struct bch_pd_controller tiering_pd;
747 struct mutex uevent_lock;
748 struct kobj_uevent_env uevent_env;
751 struct dentry *debug;
752 struct btree_debug btree_debug[BTREE_ID_NR];
753 #ifdef CONFIG_BCACHE_DEBUG
754 struct btree *verify_data;
755 struct btree_node *verify_ondisk;
756 struct mutex verify_lock;
759 u64 unused_inode_hint;
762 * A btree node on disk could have too many bsets for an iterator to fit
763 * on the stack - have to dynamically allocate them
767 mempool_t btree_bounce_pool;
769 struct journal journal;
771 unsigned bucket_journal_seq;
773 /* CACHING OTHER BLOCK DEVICES */
775 struct radix_tree_root devices;
776 struct list_head cached_devs;
777 u64 cached_dev_sectors;
778 struct closure caching;
780 #define CONGESTED_MAX 1024
781 unsigned congested_last_us;
784 /* The rest of this all shows up in sysfs */
785 unsigned congested_read_threshold_us;
786 unsigned congested_write_threshold_us;
788 struct cache_accounting accounting;
789 atomic_long_t cache_read_races;
790 atomic_long_t writeback_keys_done;
791 atomic_long_t writeback_keys_failed;
793 unsigned error_limit;
794 unsigned error_decay;
796 unsigned foreground_write_ratelimit_enabled:1;
797 unsigned copy_gc_enabled:1;
798 unsigned tiering_enabled:1;
799 unsigned tiering_percent;
802 * foreground writes will be throttled when the number of free
803 * buckets is below this percentage
805 unsigned foreground_target_percent;
807 #define BCH_DEBUG_PARAM(name, description) bool name;
808 BCH_DEBUG_PARAMS_ALL()
809 #undef BCH_DEBUG_PARAM
811 #define BCH_TIME_STAT(name, frequency_units, duration_units) \
812 struct time_stats name##_time;
817 static inline unsigned bucket_pages(const struct cache *ca)
819 return ca->mi.bucket_size / PAGE_SECTORS;
822 static inline unsigned bucket_bytes(const struct cache *ca)
824 return ca->mi.bucket_size << 9;
827 static inline unsigned block_bytes(const struct cache_set *c)
829 return c->sb.block_size << 9;
832 #endif /* _BCACHE_H */