linux/fs/btrfs/extent_io.h
Josef Bacik 196d59ab9c btrfs: switch extent buffer tree lock to rw_semaphore
Historically we've implemented our own locking because we wanted to be
able to selectively spin or sleep based on what we were doing in the
tree.  For instance, if all of our nodes were in cache then there's
rarely a reason to need to sleep waiting for node locks, as they'll
likely become available soon.  At the time this code was written the
rw_semaphore didn't do adaptive spinning, and thus was orders of
magnitude slower than our home grown locking.

However now the opposite is the case.  There are a few problems with how
we implement blocking locks, namely that we use a normal waitqueue and
simply wake everybody up in reverse sleep order.  This leads to some
suboptimal performance behavior, and a lot of context switches in highly
contended cases.  The rw_semaphores actually do this properly, and also
have adaptive spinning that works relatively well.

The locking code is also a bit of a bear to understand, and we lose the
benefit of lockdep for the most part because the blocking states of the
lock are simply ad-hoc and not mapped into lockdep.

So rework the locking code to drop all of this custom locking stuff, and
simply use a rw_semaphore for everything.  This makes the locking much
simpler for everything, as we can now drop a lot of cruft and blocking
transitions.  The performance numbers vary depending on the workload,
because generally speaking there doesn't tend to be a lot of contention
on the btree.  However, on my test system which is an 80 core single
socket system with 256GiB of RAM and a 2TiB NVMe drive I get the
following results (with all debug options off):

  dbench 200 baseline
  Throughput 216.056 MB/sec  200 clients  200 procs  max_latency=1471.197 ms

  dbench 200 with patch
  Throughput 737.188 MB/sec  200 clients  200 procs  max_latency=714.346 ms

Previously we also used fs_mark to test this sort of contention, and
those results are far less impressive, mostly because there's not enough
tasks to really stress the locking

  fs_mark -d /d[0-15] -S 0 -L 20 -n 100000 -s 0 -t 16

  baseline
    Average Files/sec:     160166.7
    p50 Files/sec:         165832
    p90 Files/sec:         123886
    p99 Files/sec:         123495

    real    3m26.527s
    user    2m19.223s
    sys     48m21.856s

  patched
    Average Files/sec:     164135.7
    p50 Files/sec:         171095
    p90 Files/sec:         122889
    p99 Files/sec:         113819

    real    3m29.660s
    user    2m19.990s
    sys     44m12.259s

Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2020-12-08 15:53:43 +01:00

313 lines
10 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef BTRFS_EXTENT_IO_H
#define BTRFS_EXTENT_IO_H
#include <linux/rbtree.h>
#include <linux/refcount.h>
#include <linux/fiemap.h>
#include "ulist.h"
/*
* flags for bio submission. The high bits indicate the compression
* type for this bio
*/
#define EXTENT_BIO_COMPRESSED 1
#define EXTENT_BIO_FLAG_SHIFT 16
enum {
EXTENT_BUFFER_UPTODATE,
EXTENT_BUFFER_DIRTY,
EXTENT_BUFFER_CORRUPT,
/* this got triggered by readahead */
EXTENT_BUFFER_READAHEAD,
EXTENT_BUFFER_TREE_REF,
EXTENT_BUFFER_STALE,
EXTENT_BUFFER_WRITEBACK,
/* read IO error */
EXTENT_BUFFER_READ_ERR,
EXTENT_BUFFER_UNMAPPED,
EXTENT_BUFFER_IN_TREE,
/* write IO error */
EXTENT_BUFFER_WRITE_ERR,
};
/* these are flags for __process_pages_contig */
#define PAGE_UNLOCK (1 << 0)
#define PAGE_CLEAR_DIRTY (1 << 1)
#define PAGE_SET_WRITEBACK (1 << 2)
#define PAGE_END_WRITEBACK (1 << 3)
#define PAGE_SET_PRIVATE2 (1 << 4)
#define PAGE_SET_ERROR (1 << 5)
#define PAGE_LOCK (1 << 6)
/*
* page->private values. Every page that is controlled by the extent
* map has page->private set to one.
*/
#define EXTENT_PAGE_PRIVATE 1
/*
* The extent buffer bitmap operations are done with byte granularity instead of
* word granularity for two reasons:
* 1. The bitmaps must be little-endian on disk.
* 2. Bitmap items are not guaranteed to be aligned to a word and therefore a
* single word in a bitmap may straddle two pages in the extent buffer.
*/
#define BIT_BYTE(nr) ((nr) / BITS_PER_BYTE)
#define BYTE_MASK ((1 << BITS_PER_BYTE) - 1)
#define BITMAP_FIRST_BYTE_MASK(start) \
((BYTE_MASK << ((start) & (BITS_PER_BYTE - 1))) & BYTE_MASK)
#define BITMAP_LAST_BYTE_MASK(nbits) \
(BYTE_MASK >> (-(nbits) & (BITS_PER_BYTE - 1)))
struct btrfs_root;
struct btrfs_inode;
struct btrfs_io_bio;
struct io_failure_record;
struct extent_io_tree;
typedef blk_status_t (submit_bio_hook_t)(struct inode *inode, struct bio *bio,
int mirror_num,
unsigned long bio_flags);
typedef blk_status_t (extent_submit_bio_start_t)(void *private_data,
struct bio *bio, u64 bio_offset);
#define INLINE_EXTENT_BUFFER_PAGES 16
#define MAX_INLINE_EXTENT_BUFFER_SIZE (INLINE_EXTENT_BUFFER_PAGES * PAGE_SIZE)
struct extent_buffer {
u64 start;
unsigned long len;
unsigned long bflags;
struct btrfs_fs_info *fs_info;
spinlock_t refs_lock;
atomic_t refs;
atomic_t io_pages;
int read_mirror;
struct rcu_head rcu_head;
pid_t lock_owner;
bool lock_recursed;
struct rw_semaphore lock;
/* >= 0 if eb belongs to a log tree, -1 otherwise */
short log_index;
struct page *pages[INLINE_EXTENT_BUFFER_PAGES];
#ifdef CONFIG_BTRFS_DEBUG
struct list_head leak_list;
#endif
};
/*
* Structure to record how many bytes and which ranges are set/cleared
*/
struct extent_changeset {
/* How many bytes are set/cleared in this operation */
unsigned int bytes_changed;
/* Changed ranges */
struct ulist range_changed;
};
static inline void extent_changeset_init(struct extent_changeset *changeset)
{
changeset->bytes_changed = 0;
ulist_init(&changeset->range_changed);
}
static inline struct extent_changeset *extent_changeset_alloc(void)
{
struct extent_changeset *ret;
ret = kmalloc(sizeof(*ret), GFP_KERNEL);
if (!ret)
return NULL;
extent_changeset_init(ret);
return ret;
}
static inline void extent_changeset_release(struct extent_changeset *changeset)
{
if (!changeset)
return;
changeset->bytes_changed = 0;
ulist_release(&changeset->range_changed);
}
static inline void extent_changeset_free(struct extent_changeset *changeset)
{
if (!changeset)
return;
extent_changeset_release(changeset);
kfree(changeset);
}
static inline void extent_set_compress_type(unsigned long *bio_flags,
int compress_type)
{
*bio_flags |= compress_type << EXTENT_BIO_FLAG_SHIFT;
}
static inline int extent_compress_type(unsigned long bio_flags)
{
return bio_flags >> EXTENT_BIO_FLAG_SHIFT;
}
struct extent_map_tree;
typedef struct extent_map *(get_extent_t)(struct btrfs_inode *inode,
struct page *page, size_t pg_offset,
u64 start, u64 len);
int try_release_extent_mapping(struct page *page, gfp_t mask);
int try_release_extent_buffer(struct page *page);
int __must_check submit_one_bio(struct bio *bio, int mirror_num,
unsigned long bio_flags);
int btrfs_do_readpage(struct page *page, struct extent_map **em_cached,
struct bio **bio, unsigned long *bio_flags,
unsigned int read_flags, u64 *prev_em_start);
int extent_write_full_page(struct page *page, struct writeback_control *wbc);
int extent_write_locked_range(struct inode *inode, u64 start, u64 end,
int mode);
int extent_writepages(struct address_space *mapping,
struct writeback_control *wbc);
int btree_write_cache_pages(struct address_space *mapping,
struct writeback_control *wbc);
void extent_readahead(struct readahead_control *rac);
int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo,
u64 start, u64 len);
void set_page_extent_mapped(struct page *page);
struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
u64 start);
struct extent_buffer *__alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
u64 start, unsigned long len);
struct extent_buffer *alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
u64 start);
struct extent_buffer *btrfs_clone_extent_buffer(const struct extent_buffer *src);
struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info,
u64 start);
void free_extent_buffer(struct extent_buffer *eb);
void free_extent_buffer_stale(struct extent_buffer *eb);
#define WAIT_NONE 0
#define WAIT_COMPLETE 1
#define WAIT_PAGE_LOCK 2
int read_extent_buffer_pages(struct extent_buffer *eb, int wait,
int mirror_num);
void wait_on_extent_buffer_writeback(struct extent_buffer *eb);
static inline int num_extent_pages(const struct extent_buffer *eb)
{
return (round_up(eb->start + eb->len, PAGE_SIZE) >> PAGE_SHIFT) -
(eb->start >> PAGE_SHIFT);
}
static inline int extent_buffer_uptodate(const struct extent_buffer *eb)
{
return test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
}
int memcmp_extent_buffer(const struct extent_buffer *eb, const void *ptrv,
unsigned long start, unsigned long len);
void read_extent_buffer(const struct extent_buffer *eb, void *dst,
unsigned long start,
unsigned long len);
int read_extent_buffer_to_user_nofault(const struct extent_buffer *eb,
void __user *dst, unsigned long start,
unsigned long len);
void write_extent_buffer_fsid(const struct extent_buffer *eb, const void *src);
void write_extent_buffer_chunk_tree_uuid(const struct extent_buffer *eb,
const void *src);
void write_extent_buffer(const struct extent_buffer *eb, const void *src,
unsigned long start, unsigned long len);
void copy_extent_buffer_full(const struct extent_buffer *dst,
const struct extent_buffer *src);
void copy_extent_buffer(const struct extent_buffer *dst,
const struct extent_buffer *src,
unsigned long dst_offset, unsigned long src_offset,
unsigned long len);
void memcpy_extent_buffer(const struct extent_buffer *dst,
unsigned long dst_offset, unsigned long src_offset,
unsigned long len);
void memmove_extent_buffer(const struct extent_buffer *dst,
unsigned long dst_offset, unsigned long src_offset,
unsigned long len);
void memzero_extent_buffer(const struct extent_buffer *eb, unsigned long start,
unsigned long len);
int extent_buffer_test_bit(const struct extent_buffer *eb, unsigned long start,
unsigned long pos);
void extent_buffer_bitmap_set(const struct extent_buffer *eb, unsigned long start,
unsigned long pos, unsigned long len);
void extent_buffer_bitmap_clear(const struct extent_buffer *eb,
unsigned long start, unsigned long pos,
unsigned long len);
void clear_extent_buffer_dirty(const struct extent_buffer *eb);
bool set_extent_buffer_dirty(struct extent_buffer *eb);
void set_extent_buffer_uptodate(struct extent_buffer *eb);
void clear_extent_buffer_uptodate(struct extent_buffer *eb);
int extent_buffer_under_io(const struct extent_buffer *eb);
void extent_range_clear_dirty_for_io(struct inode *inode, u64 start, u64 end);
void extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end);
void extent_clear_unlock_delalloc(struct btrfs_inode *inode, u64 start, u64 end,
struct page *locked_page,
unsigned bits_to_clear,
unsigned long page_ops);
struct bio *btrfs_bio_alloc(u64 first_byte);
struct bio *btrfs_io_bio_alloc(unsigned int nr_iovecs);
struct bio *btrfs_bio_clone(struct bio *bio);
struct bio *btrfs_bio_clone_partial(struct bio *orig, int offset, int size);
struct btrfs_fs_info;
struct btrfs_inode;
int repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start,
u64 length, u64 logical, struct page *page,
unsigned int pg_offset, int mirror_num);
void end_extent_writepage(struct page *page, int err, u64 start, u64 end);
int btrfs_repair_eb_io_failure(const struct extent_buffer *eb, int mirror_num);
/*
* When IO fails, either with EIO or csum verification fails, we
* try other mirrors that might have a good copy of the data. This
* io_failure_record is used to record state as we go through all the
* mirrors. If another mirror has good data, the page is set up to date
* and things continue. If a good mirror can't be found, the original
* bio end_io callback is called to indicate things have failed.
*/
struct io_failure_record {
struct page *page;
u64 start;
u64 len;
u64 logical;
unsigned long bio_flags;
int this_mirror;
int failed_mirror;
int in_validation;
};
blk_status_t btrfs_submit_read_repair(struct inode *inode,
struct bio *failed_bio, u64 phy_offset,
struct page *page, unsigned int pgoff,
u64 start, u64 end, int failed_mirror,
submit_bio_hook_t *submit_bio_hook);
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
bool find_lock_delalloc_range(struct inode *inode,
struct page *locked_page, u64 *start,
u64 *end);
#endif
struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info,
u64 start);
#ifdef CONFIG_BTRFS_DEBUG
void btrfs_extent_buffer_leak_debug_check(struct btrfs_fs_info *fs_info);
#else
#define btrfs_extent_buffer_leak_debug_check(fs_info) do {} while (0)
#endif
#endif