mirror of
https://github.com/torvalds/linux.git
synced 2024-12-04 18:13:04 +00:00
b9efa9673e
The btree write buffer takes as input keys from the journal, sorts them, deduplicates them, and flushes them back to the btree in sorted order. The disk space accounting rewrite is moving accounting to normal btree keys, with update (in this case deltas) accumulated in the write buffer and then flushed to the btree; but this is going to increase the number of keys handled by the write buffer by perhaps as much as a factor of 3x-5x. The overhead from copying around and sorting this many keys would cause a significant performance regression, but: there is huge locality in updates to accounting keys that we can take advantage of. Instead of appending accounting keys to the list of keys to be sorted, this patch adds an eytzinger search tree of recently seen accounting keys. We look up the accounting key in the eytzinger search tree and apply the delta directly, adding it if it doesn't exist, and periodically prune the eytzinger tree of unused entries. Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
106 lines
3.2 KiB
C
106 lines
3.2 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _BCACHEFS_BTREE_WRITE_BUFFER_H
|
|
#define _BCACHEFS_BTREE_WRITE_BUFFER_H
|
|
|
|
#include "bkey.h"
|
|
#include "disk_accounting.h"
|
|
|
|
static inline bool bch2_btree_write_buffer_should_flush(struct bch_fs *c)
|
|
{
|
|
struct btree_write_buffer *wb = &c->btree_write_buffer;
|
|
|
|
return wb->inc.keys.nr + wb->flushing.keys.nr > wb->inc.keys.size / 4;
|
|
}
|
|
|
|
static inline bool bch2_btree_write_buffer_must_wait(struct bch_fs *c)
|
|
{
|
|
struct btree_write_buffer *wb = &c->btree_write_buffer;
|
|
|
|
return wb->inc.keys.nr > wb->inc.keys.size * 3 / 4;
|
|
}
|
|
|
|
struct btree_trans;
|
|
int bch2_btree_write_buffer_flush_sync(struct btree_trans *);
|
|
int bch2_btree_write_buffer_flush_nocheck_rw(struct btree_trans *);
|
|
int bch2_btree_write_buffer_tryflush(struct btree_trans *);
|
|
|
|
struct bkey_buf;
|
|
int bch2_btree_write_buffer_maybe_flush(struct btree_trans *, struct bkey_s_c, struct bkey_buf *);
|
|
|
|
struct journal_keys_to_wb {
|
|
struct btree_write_buffer_keys *wb;
|
|
size_t room;
|
|
u64 seq;
|
|
};
|
|
|
|
static inline int wb_key_cmp(const void *_l, const void *_r)
|
|
{
|
|
const struct btree_write_buffered_key *l = _l;
|
|
const struct btree_write_buffered_key *r = _r;
|
|
|
|
return cmp_int(l->btree, r->btree) ?: bpos_cmp(l->k.k.p, r->k.k.p);
|
|
}
|
|
|
|
int bch2_accounting_key_to_wb_slowpath(struct bch_fs *,
|
|
enum btree_id, struct bkey_i_accounting *);
|
|
|
|
static inline int bch2_accounting_key_to_wb(struct bch_fs *c,
|
|
enum btree_id btree, struct bkey_i_accounting *k)
|
|
{
|
|
struct btree_write_buffer *wb = &c->btree_write_buffer;
|
|
struct btree_write_buffered_key search;
|
|
search.btree = btree;
|
|
search.k.k.p = k->k.p;
|
|
|
|
unsigned idx = eytzinger0_find(wb->accounting.data, wb->accounting.nr,
|
|
sizeof(wb->accounting.data[0]),
|
|
wb_key_cmp, &search);
|
|
|
|
if (idx >= wb->accounting.nr)
|
|
return bch2_accounting_key_to_wb_slowpath(c, btree, k);
|
|
|
|
struct bkey_i_accounting *dst = bkey_i_to_accounting(&wb->accounting.data[idx].k);
|
|
bch2_accounting_accumulate(dst, accounting_i_to_s_c(k));
|
|
return 0;
|
|
}
|
|
|
|
int bch2_journal_key_to_wb_slowpath(struct bch_fs *,
|
|
struct journal_keys_to_wb *,
|
|
enum btree_id, struct bkey_i *);
|
|
|
|
static inline int __bch2_journal_key_to_wb(struct bch_fs *c,
|
|
struct journal_keys_to_wb *dst,
|
|
enum btree_id btree, struct bkey_i *k)
|
|
{
|
|
if (unlikely(!dst->room))
|
|
return bch2_journal_key_to_wb_slowpath(c, dst, btree, k);
|
|
|
|
struct btree_write_buffered_key *wb_k = &darray_top(dst->wb->keys);
|
|
wb_k->journal_seq = dst->seq;
|
|
wb_k->btree = btree;
|
|
bkey_copy(&wb_k->k, k);
|
|
dst->wb->keys.nr++;
|
|
dst->room--;
|
|
return 0;
|
|
}
|
|
|
|
static inline int bch2_journal_key_to_wb(struct bch_fs *c,
|
|
struct journal_keys_to_wb *dst,
|
|
enum btree_id btree, struct bkey_i *k)
|
|
{
|
|
EBUG_ON(!dst->seq);
|
|
|
|
return k->k.type == KEY_TYPE_accounting
|
|
? bch2_accounting_key_to_wb(c, btree, bkey_i_to_accounting(k))
|
|
: __bch2_journal_key_to_wb(c, dst, btree, k);
|
|
}
|
|
|
|
void bch2_journal_keys_to_write_buffer_start(struct bch_fs *, struct journal_keys_to_wb *, u64);
|
|
int bch2_journal_keys_to_write_buffer_end(struct bch_fs *, struct journal_keys_to_wb *);
|
|
|
|
int bch2_btree_write_buffer_resize(struct bch_fs *, size_t);
|
|
void bch2_fs_btree_write_buffer_exit(struct bch_fs *);
|
|
int bch2_fs_btree_write_buffer_init(struct bch_fs *);
|
|
|
|
#endif /* _BCACHEFS_BTREE_WRITE_BUFFER_H */
|