linux/fs/btrfs/extent_map.c
Josef Bacik 5dc562c541 Btrfs: turbo charge fsync
At least for the vm workload.  Currently on fsync we will

1) Truncate all items in the log tree for the given inode if they exist

and

2) Copy all items for a given inode into the log

The problem with this is that for things like VMs you can have lots of
extents from the fragmented writing behavior, and worst yet you may have
only modified a few extents, not the entire thing.  This patch fixes this
problem by tracking which transid modified our extent, and then when we do
the tree logging we find all of the extents we've modified in our current
transaction, sort them and commit them.  We also only truncate up to the
xattrs of the inode and copy that stuff in normally, and then just drop any
extents in the range we have that exist in the log already.  Here are some
numbers of a 50 meg fio job that does random writes and fsync()s after every
write

		Original	Patched
SATA drive	82KB/s		140KB/s
Fusion drive	431KB/s		2532KB/s

So around 2-6 times faster depending on your hardware.  There are a few
corner cases, for example if you truncate at all we have to do it the old
way since there is no way to be sure what is in the log is ok.  This
probably could be done smarter, but if you write-fsync-truncate-write-fsync
you deserve what you get.  All this work is in RAM of course so if your
inode gets evicted from cache and you read it in and fsync it we'll do it
the slow way if we are still in the same transaction that we last modified
the inode in.

The biggest cool part of this is that it requires no changes to the recovery
code, so if you fsync with this patch and crash and load an old kernel, it
will run the recovery and be a-ok.  I have tested this pretty thoroughly
with an fsync tester and everything comes back fine, as well as xfstests.
Thanks,

Signed-off-by: Josef Bacik <jbacik@fusionio.com>
2012-10-01 15:19:03 -04:00

394 lines
9.7 KiB
C

#include <linux/err.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/spinlock.h>
#include <linux/hardirq.h>
#include "ctree.h"
#include "extent_map.h"
static struct kmem_cache *extent_map_cache;
int __init extent_map_init(void)
{
extent_map_cache = kmem_cache_create("extent_map",
sizeof(struct extent_map), 0,
SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD, NULL);
if (!extent_map_cache)
return -ENOMEM;
return 0;
}
void extent_map_exit(void)
{
if (extent_map_cache)
kmem_cache_destroy(extent_map_cache);
}
/**
* extent_map_tree_init - initialize extent map tree
* @tree: tree to initialize
*
* Initialize the extent tree @tree. Should be called for each new inode
* or other user of the extent_map interface.
*/
void extent_map_tree_init(struct extent_map_tree *tree)
{
tree->map = RB_ROOT;
INIT_LIST_HEAD(&tree->modified_extents);
rwlock_init(&tree->lock);
}
/**
* alloc_extent_map - allocate new extent map structure
*
* Allocate a new extent_map structure. The new structure is
* returned with a reference count of one and needs to be
* freed using free_extent_map()
*/
struct extent_map *alloc_extent_map(void)
{
struct extent_map *em;
em = kmem_cache_alloc(extent_map_cache, GFP_NOFS);
if (!em)
return NULL;
em->in_tree = 0;
em->flags = 0;
em->compress_type = BTRFS_COMPRESS_NONE;
em->generation = 0;
atomic_set(&em->refs, 1);
INIT_LIST_HEAD(&em->list);
return em;
}
/**
* free_extent_map - drop reference count of an extent_map
* @em: extent map beeing releasead
*
* Drops the reference out on @em by one and free the structure
* if the reference count hits zero.
*/
void free_extent_map(struct extent_map *em)
{
if (!em)
return;
WARN_ON(atomic_read(&em->refs) == 0);
if (atomic_dec_and_test(&em->refs)) {
WARN_ON(em->in_tree);
WARN_ON(!list_empty(&em->list));
kmem_cache_free(extent_map_cache, em);
}
}
static struct rb_node *tree_insert(struct rb_root *root, u64 offset,
struct rb_node *node)
{
struct rb_node **p = &root->rb_node;
struct rb_node *parent = NULL;
struct extent_map *entry;
while (*p) {
parent = *p;
entry = rb_entry(parent, struct extent_map, rb_node);
WARN_ON(!entry->in_tree);
if (offset < entry->start)
p = &(*p)->rb_left;
else if (offset >= extent_map_end(entry))
p = &(*p)->rb_right;
else
return parent;
}
entry = rb_entry(node, struct extent_map, rb_node);
entry->in_tree = 1;
rb_link_node(node, parent, p);
rb_insert_color(node, root);
return NULL;
}
/*
* search through the tree for an extent_map with a given offset. If
* it can't be found, try to find some neighboring extents
*/
static struct rb_node *__tree_search(struct rb_root *root, u64 offset,
struct rb_node **prev_ret,
struct rb_node **next_ret)
{
struct rb_node *n = root->rb_node;
struct rb_node *prev = NULL;
struct rb_node *orig_prev = NULL;
struct extent_map *entry;
struct extent_map *prev_entry = NULL;
while (n) {
entry = rb_entry(n, struct extent_map, rb_node);
prev = n;
prev_entry = entry;
WARN_ON(!entry->in_tree);
if (offset < entry->start)
n = n->rb_left;
else if (offset >= extent_map_end(entry))
n = n->rb_right;
else
return n;
}
if (prev_ret) {
orig_prev = prev;
while (prev && offset >= extent_map_end(prev_entry)) {
prev = rb_next(prev);
prev_entry = rb_entry(prev, struct extent_map, rb_node);
}
*prev_ret = prev;
prev = orig_prev;
}
if (next_ret) {
prev_entry = rb_entry(prev, struct extent_map, rb_node);
while (prev && offset < prev_entry->start) {
prev = rb_prev(prev);
prev_entry = rb_entry(prev, struct extent_map, rb_node);
}
*next_ret = prev;
}
return NULL;
}
/* check to see if two extent_map structs are adjacent and safe to merge */
static int mergable_maps(struct extent_map *prev, struct extent_map *next)
{
if (test_bit(EXTENT_FLAG_PINNED, &prev->flags))
return 0;
/*
* don't merge compressed extents, we need to know their
* actual size
*/
if (test_bit(EXTENT_FLAG_COMPRESSED, &prev->flags))
return 0;
if (extent_map_end(prev) == next->start &&
prev->flags == next->flags &&
prev->bdev == next->bdev &&
((next->block_start == EXTENT_MAP_HOLE &&
prev->block_start == EXTENT_MAP_HOLE) ||
(next->block_start == EXTENT_MAP_INLINE &&
prev->block_start == EXTENT_MAP_INLINE) ||
(next->block_start == EXTENT_MAP_DELALLOC &&
prev->block_start == EXTENT_MAP_DELALLOC) ||
(next->block_start < EXTENT_MAP_LAST_BYTE - 1 &&
next->block_start == extent_map_block_end(prev)))) {
return 1;
}
return 0;
}
static void try_merge_map(struct extent_map_tree *tree, struct extent_map *em)
{
struct extent_map *merge = NULL;
struct rb_node *rb;
if (em->start != 0) {
rb = rb_prev(&em->rb_node);
if (rb)
merge = rb_entry(rb, struct extent_map, rb_node);
if (rb && mergable_maps(merge, em)) {
em->start = merge->start;
em->len += merge->len;
em->block_len += merge->block_len;
em->block_start = merge->block_start;
merge->in_tree = 0;
if (merge->generation > em->generation) {
em->generation = merge->generation;
list_move(&em->list, &tree->modified_extents);
}
list_del_init(&merge->list);
rb_erase(&merge->rb_node, &tree->map);
free_extent_map(merge);
}
}
rb = rb_next(&em->rb_node);
if (rb)
merge = rb_entry(rb, struct extent_map, rb_node);
if (rb && mergable_maps(em, merge)) {
em->len += merge->len;
em->block_len += merge->len;
rb_erase(&merge->rb_node, &tree->map);
merge->in_tree = 0;
if (merge->generation > em->generation) {
em->generation = merge->generation;
list_move(&em->list, &tree->modified_extents);
}
list_del_init(&merge->list);
free_extent_map(merge);
}
}
/**
* unpint_extent_cache - unpin an extent from the cache
* @tree: tree to unpin the extent in
* @start: logical offset in the file
* @len: length of the extent
* @gen: generation that this extent has been modified in
* @prealloc: if this is set we need to clear the prealloc flag
*
* Called after an extent has been written to disk properly. Set the generation
* to the generation that actually added the file item to the inode so we know
* we need to sync this extent when we call fsync().
*/
int unpin_extent_cache(struct extent_map_tree *tree, u64 start, u64 len,
u64 gen)
{
int ret = 0;
struct extent_map *em;
write_lock(&tree->lock);
em = lookup_extent_mapping(tree, start, len);
WARN_ON(!em || em->start != start);
if (!em)
goto out;
list_move(&em->list, &tree->modified_extents);
em->generation = gen;
clear_bit(EXTENT_FLAG_PINNED, &em->flags);
try_merge_map(tree, em);
free_extent_map(em);
out:
write_unlock(&tree->lock);
return ret;
}
/**
* add_extent_mapping - add new extent map to the extent tree
* @tree: tree to insert new map in
* @em: map to insert
*
* Insert @em into @tree or perform a simple forward/backward merge with
* existing mappings. The extent_map struct passed in will be inserted
* into the tree directly, with an additional reference taken, or a
* reference dropped if the merge attempt was successful.
*/
int add_extent_mapping(struct extent_map_tree *tree,
struct extent_map *em)
{
int ret = 0;
struct rb_node *rb;
struct extent_map *exist;
exist = lookup_extent_mapping(tree, em->start, em->len);
if (exist) {
free_extent_map(exist);
ret = -EEXIST;
goto out;
}
rb = tree_insert(&tree->map, em->start, &em->rb_node);
if (rb) {
ret = -EEXIST;
goto out;
}
atomic_inc(&em->refs);
try_merge_map(tree, em);
out:
return ret;
}
/* simple helper to do math around the end of an extent, handling wrap */
static u64 range_end(u64 start, u64 len)
{
if (start + len < start)
return (u64)-1;
return start + len;
}
struct extent_map *__lookup_extent_mapping(struct extent_map_tree *tree,
u64 start, u64 len, int strict)
{
struct extent_map *em;
struct rb_node *rb_node;
struct rb_node *prev = NULL;
struct rb_node *next = NULL;
u64 end = range_end(start, len);
rb_node = __tree_search(&tree->map, start, &prev, &next);
if (!rb_node) {
if (prev)
rb_node = prev;
else if (next)
rb_node = next;
else
return NULL;
}
em = rb_entry(rb_node, struct extent_map, rb_node);
if (strict && !(end > em->start && start < extent_map_end(em)))
return NULL;
atomic_inc(&em->refs);
return em;
}
/**
* lookup_extent_mapping - lookup extent_map
* @tree: tree to lookup in
* @start: byte offset to start the search
* @len: length of the lookup range
*
* Find and return the first extent_map struct in @tree that intersects the
* [start, len] range. There may be additional objects in the tree that
* intersect, so check the object returned carefully to make sure that no
* additional lookups are needed.
*/
struct extent_map *lookup_extent_mapping(struct extent_map_tree *tree,
u64 start, u64 len)
{
return __lookup_extent_mapping(tree, start, len, 1);
}
/**
* search_extent_mapping - find a nearby extent map
* @tree: tree to lookup in
* @start: byte offset to start the search
* @len: length of the lookup range
*
* Find and return the first extent_map struct in @tree that intersects the
* [start, len] range.
*
* If one can't be found, any nearby extent may be returned
*/
struct extent_map *search_extent_mapping(struct extent_map_tree *tree,
u64 start, u64 len)
{
return __lookup_extent_mapping(tree, start, len, 0);
}
/**
* remove_extent_mapping - removes an extent_map from the extent tree
* @tree: extent tree to remove from
* @em: extent map beeing removed
*
* Removes @em from @tree. No reference counts are dropped, and no checks
* are done to see if the range is in use
*/
int remove_extent_mapping(struct extent_map_tree *tree, struct extent_map *em)
{
int ret = 0;
WARN_ON(test_bit(EXTENT_FLAG_PINNED, &em->flags));
rb_erase(&em->rb_node, &tree->map);
list_del_init(&em->list);
em->in_tree = 0;
return ret;
}