linux/fs/btrfs/ordered-data.c

981 lines
27 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 2007 Oracle. All rights reserved.
*/
#include <linux/slab.h>
#include <linux/blkdev.h>
#include <linux/writeback.h>
#include <linux/sched/mm.h>
#include "ctree.h"
#include "transaction.h"
#include "btrfs_inode.h"
#include "extent_io.h"
#include "disk-io.h"
#include "compression.h"
static struct kmem_cache *btrfs_ordered_extent_cache;
static u64 entry_end(struct btrfs_ordered_extent *entry)
{
if (entry->file_offset + entry->len < entry->file_offset)
return (u64)-1;
return entry->file_offset + entry->len;
}
/* returns NULL if the insertion worked, or it returns the node it did find
* in the tree
*/
static struct rb_node *tree_insert(struct rb_root *root, u64 file_offset,
struct rb_node *node)
{
struct rb_node **p = &root->rb_node;
struct rb_node *parent = NULL;
struct btrfs_ordered_extent *entry;
while (*p) {
parent = *p;
entry = rb_entry(parent, struct btrfs_ordered_extent, rb_node);
if (file_offset < entry->file_offset)
p = &(*p)->rb_left;
else if (file_offset >= entry_end(entry))
p = &(*p)->rb_right;
else
return parent;
}
rb_link_node(node, parent, p);
rb_insert_color(node, root);
return NULL;
}
static void ordered_data_tree_panic(struct inode *inode, int errno,
u64 offset)
{
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
btrfs_panic(fs_info, errno,
"Inconsistency in ordered tree at offset %llu", offset);
}
/*
* look for a given offset in the tree, and if it can't be found return the
* first lesser offset
*/
static struct rb_node *__tree_search(struct rb_root *root, u64 file_offset,
struct rb_node **prev_ret)
{
struct rb_node *n = root->rb_node;
struct rb_node *prev = NULL;
struct rb_node *test;
struct btrfs_ordered_extent *entry;
struct btrfs_ordered_extent *prev_entry = NULL;
while (n) {
entry = rb_entry(n, struct btrfs_ordered_extent, rb_node);
prev = n;
prev_entry = entry;
if (file_offset < entry->file_offset)
n = n->rb_left;
else if (file_offset >= entry_end(entry))
n = n->rb_right;
else
return n;
}
if (!prev_ret)
return NULL;
while (prev && file_offset >= entry_end(prev_entry)) {
test = rb_next(prev);
if (!test)
break;
prev_entry = rb_entry(test, struct btrfs_ordered_extent,
rb_node);
if (file_offset < entry_end(prev_entry))
break;
prev = test;
}
if (prev)
prev_entry = rb_entry(prev, struct btrfs_ordered_extent,
rb_node);
while (prev && file_offset < entry_end(prev_entry)) {
test = rb_prev(prev);
if (!test)
break;
prev_entry = rb_entry(test, struct btrfs_ordered_extent,
rb_node);
prev = test;
}
*prev_ret = prev;
return NULL;
}
/*
* helper to check if a given offset is inside a given entry
*/
static int offset_in_entry(struct btrfs_ordered_extent *entry, u64 file_offset)
{
if (file_offset < entry->file_offset ||
entry->file_offset + entry->len <= file_offset)
return 0;
return 1;
}
static int range_overlaps(struct btrfs_ordered_extent *entry, u64 file_offset,
u64 len)
{
if (file_offset + len <= entry->file_offset ||
entry->file_offset + entry->len <= file_offset)
return 0;
return 1;
}
/*
* look find the first ordered struct that has this offset, otherwise
* the first one less than this offset
*/
static inline struct rb_node *tree_search(struct btrfs_ordered_inode_tree *tree,
u64 file_offset)
{
struct rb_root *root = &tree->tree;
struct rb_node *prev = NULL;
struct rb_node *ret;
struct btrfs_ordered_extent *entry;
if (tree->last) {
entry = rb_entry(tree->last, struct btrfs_ordered_extent,
rb_node);
if (offset_in_entry(entry, file_offset))
return tree->last;
}
ret = __tree_search(root, file_offset, &prev);
if (!ret)
ret = prev;
if (ret)
tree->last = ret;
return ret;
}
/* allocate and add a new ordered_extent into the per-inode tree.
* file_offset is the logical offset in the file
*
* start is the disk block number of an extent already reserved in the
* extent allocation tree
*
* len is the length of the extent
*
* The tree is given a single reference on the ordered extent that was
* inserted.
*/
static int __btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
u64 start, u64 len, u64 disk_len,
int type, int dio, int compress_type)
{
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_ordered_inode_tree *tree;
struct rb_node *node;
struct btrfs_ordered_extent *entry;
tree = &BTRFS_I(inode)->ordered_tree;
entry = kmem_cache_zalloc(btrfs_ordered_extent_cache, GFP_NOFS);
if (!entry)
return -ENOMEM;
entry->file_offset = file_offset;
entry->start = start;
entry->len = len;
Btrfs: Add zlib compression support This is a large change for adding compression on reading and writing, both for inline and regular extents. It does some fairly large surgery to the writeback paths. Compression is off by default and enabled by mount -o compress. Even when the -o compress mount option is not used, it is possible to read compressed extents off the disk. If compression for a given set of pages fails to make them smaller, the file is flagged to avoid future compression attempts later. * While finding delalloc extents, the pages are locked before being sent down to the delalloc handler. This allows the delalloc handler to do complex things such as cleaning the pages, marking them writeback and starting IO on their behalf. * Inline extents are inserted at delalloc time now. This allows us to compress the data before inserting the inline extent, and it allows us to insert an inline extent that spans multiple pages. * All of the in-memory extent representations (extent_map.c, ordered-data.c etc) are changed to record both an in-memory size and an on disk size, as well as a flag for compression. From a disk format point of view, the extent pointers in the file are changed to record the on disk size of a given extent and some encoding flags. Space in the disk format is allocated for compression encoding, as well as encryption and a generic 'other' field. Neither the encryption or the 'other' field are currently used. In order to limit the amount of data read for a single random read in the file, the size of a compressed extent is limited to 128k. This is a software only limit, the disk format supports u64 sized compressed extents. In order to limit the ram consumed while processing extents, the uncompressed size of a compressed extent is limited to 256k. This is a software only limit and will be subject to tuning later. Checksumming is still done on compressed extents, and it is done on the uncompressed version of the data. This way additional encodings can be layered on without having to figure out which encoding to checksum. Compression happens at delalloc time, which is basically singled threaded because it is usually done by a single pdflush thread. This makes it tricky to spread the compression load across all the cpus on the box. We'll have to look at parallel pdflush walks of dirty inodes at a later time. Decompression is hooked into readpages and it does spread across CPUs nicely. Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-10-30 02:49:59 +08:00
entry->disk_len = disk_len;
entry->bytes_left = len;
entry->inode = igrab(inode);
entry->compress_type = compress_type;
entry->truncated_len = (u64)-1;
if (type != BTRFS_ORDERED_IO_DONE && type != BTRFS_ORDERED_COMPLETE)
set_bit(type, &entry->flags);
if (dio) {
percpu_counter_add_batch(&fs_info->dio_bytes, len,
fs_info->delalloc_batch);
set_bit(BTRFS_ORDERED_DIRECT, &entry->flags);
}
/* one ref for the tree */
refcount_set(&entry->refs, 1);
init_waitqueue_head(&entry->wait);
INIT_LIST_HEAD(&entry->list);
INIT_LIST_HEAD(&entry->root_extent_list);
INIT_LIST_HEAD(&entry->work_list);
init_completion(&entry->completion);
INIT_LIST_HEAD(&entry->log_list);
INIT_LIST_HEAD(&entry->trans_list);
Btrfs: add initial tracepoint support for btrfs Tracepoints can provide insight into why btrfs hits bugs and be greatly helpful for debugging, e.g dd-7822 [000] 2121.641088: btrfs_inode_request: root = 5(FS_TREE), gen = 4, ino = 256, blocks = 8, disk_i_size = 0, last_trans = 8, logged_trans = 0 dd-7822 [000] 2121.641100: btrfs_inode_new: root = 5(FS_TREE), gen = 8, ino = 257, blocks = 0, disk_i_size = 0, last_trans = 0, logged_trans = 0 btrfs-transacti-7804 [001] 2146.935420: btrfs_cow_block: root = 2(EXTENT_TREE), refs = 2, orig_buf = 29368320 (orig_level = 0), cow_buf = 29388800 (cow_level = 0) btrfs-transacti-7804 [001] 2146.935473: btrfs_cow_block: root = 1(ROOT_TREE), refs = 2, orig_buf = 29364224 (orig_level = 0), cow_buf = 29392896 (cow_level = 0) btrfs-transacti-7804 [001] 2146.972221: btrfs_transaction_commit: root = 1(ROOT_TREE), gen = 8 flush-btrfs-2-7821 [001] 2155.824210: btrfs_chunk_alloc: root = 3(CHUNK_TREE), offset = 1103101952, size = 1073741824, num_stripes = 1, sub_stripes = 0, type = DATA flush-btrfs-2-7821 [001] 2155.824241: btrfs_cow_block: root = 2(EXTENT_TREE), refs = 2, orig_buf = 29388800 (orig_level = 0), cow_buf = 29396992 (cow_level = 0) flush-btrfs-2-7821 [001] 2155.824255: btrfs_cow_block: root = 4(DEV_TREE), refs = 2, orig_buf = 29372416 (orig_level = 0), cow_buf = 29401088 (cow_level = 0) flush-btrfs-2-7821 [000] 2155.824329: btrfs_cow_block: root = 3(CHUNK_TREE), refs = 2, orig_buf = 20971520 (orig_level = 0), cow_buf = 20975616 (cow_level = 0) btrfs-endio-wri-7800 [001] 2155.898019: btrfs_cow_block: root = 5(FS_TREE), refs = 2, orig_buf = 29384704 (orig_level = 0), cow_buf = 29405184 (cow_level = 0) btrfs-endio-wri-7800 [001] 2155.898043: btrfs_cow_block: root = 7(CSUM_TREE), refs = 2, orig_buf = 29376512 (orig_level = 0), cow_buf = 29409280 (cow_level = 0) Here is what I have added: 1) ordere_extent: btrfs_ordered_extent_add btrfs_ordered_extent_remove btrfs_ordered_extent_start btrfs_ordered_extent_put These provide critical information to understand how ordered_extents are updated. 2) extent_map: btrfs_get_extent extent_map is used in both read and write cases, and it is useful for tracking how btrfs specific IO is running. 3) writepage: __extent_writepage btrfs_writepage_end_io_hook Pages are cirtical resourses and produce a lot of corner cases during writeback, so it is valuable to know how page is written to disk. 4) inode: btrfs_inode_new btrfs_inode_request btrfs_inode_evict These can show where and when a inode is created, when a inode is evicted. 5) sync: btrfs_sync_file btrfs_sync_fs These show sync arguments. 6) transaction: btrfs_transaction_commit In transaction based filesystem, it will be useful to know the generation and who does commit. 7) back reference and cow: btrfs_delayed_tree_ref btrfs_delayed_data_ref btrfs_delayed_ref_head btrfs_cow_block Btrfs natively supports back references, these tracepoints are helpful on understanding btrfs's COW mechanism. 8) chunk: btrfs_chunk_alloc btrfs_chunk_free Chunk is a link between physical offset and logical offset, and stands for space infomation in btrfs, and these are helpful on tracing space things. 9) reserved_extent: btrfs_reserved_extent_alloc btrfs_reserved_extent_free These can show how btrfs uses its space. Signed-off-by: Liu Bo <liubo2009@cn.fujitsu.com> Signed-off-by: Chris Mason <chris.mason@oracle.com>
2011-03-24 19:18:59 +08:00
trace_btrfs_ordered_extent_add(inode, entry);
spin_lock_irq(&tree->lock);
node = tree_insert(&tree->tree, file_offset,
&entry->rb_node);
if (node)
ordered_data_tree_panic(inode, -EEXIST, file_offset);
spin_unlock_irq(&tree->lock);
spin_lock(&root->ordered_extent_lock);
list_add_tail(&entry->root_extent_list,
&root->ordered_extents);
root->nr_ordered_extents++;
if (root->nr_ordered_extents == 1) {
spin_lock(&fs_info->ordered_root_lock);
BUG_ON(!list_empty(&root->ordered_root));
list_add_tail(&root->ordered_root, &fs_info->ordered_roots);
spin_unlock(&fs_info->ordered_root_lock);
}
spin_unlock(&root->ordered_extent_lock);
Btrfs: rework outstanding_extents Right now we do a lot of weird hoops around outstanding_extents in order to keep the extent count consistent. This is because we logically transfer the outstanding_extent count from the initial reservation through the set_delalloc_bits. This makes it pretty difficult to get a handle on how and when we need to mess with outstanding_extents. Fix this by revamping the rules of how we deal with outstanding_extents. Now instead everybody that is holding on to a delalloc extent is required to increase the outstanding extents count for itself. This means we'll have something like this btrfs_delalloc_reserve_metadata - outstanding_extents = 1 btrfs_set_extent_delalloc - outstanding_extents = 2 btrfs_release_delalloc_extents - outstanding_extents = 1 for an initial file write. Now take the append write where we extend an existing delalloc range but still under the maximum extent size btrfs_delalloc_reserve_metadata - outstanding_extents = 2 btrfs_set_extent_delalloc btrfs_set_bit_hook - outstanding_extents = 3 btrfs_merge_extent_hook - outstanding_extents = 2 btrfs_delalloc_release_extents - outstanding_extnets = 1 In order to make the ordered extent transition we of course must now make ordered extents carry their own outstanding_extent reservation, so for cow_file_range we end up with btrfs_add_ordered_extent - outstanding_extents = 2 clear_extent_bit - outstanding_extents = 1 btrfs_remove_ordered_extent - outstanding_extents = 0 This makes all manipulations of outstanding_extents much more explicit. Every successful call to btrfs_delalloc_reserve_metadata _must_ now be combined with btrfs_release_delalloc_extents, even in the error case, as that is the only function that actually modifies the outstanding_extents counter. The drawback to this is now we are much more likely to have transient cases where outstanding_extents is much larger than it actually should be. This could happen before as we manipulated the delalloc bits, but now it happens basically at every write. This may put more pressure on the ENOSPC flushing code, but I think making this code simpler is worth the cost. I have another change coming to mitigate this side-effect somewhat. I also added trace points for the counter manipulation. These were used by a bpf script I wrote to help track down leak issues. Signed-off-by: Josef Bacik <jbacik@fb.com> Signed-off-by: David Sterba <dsterba@suse.com>
2017-10-20 02:15:55 +08:00
/*
* We don't need the count_max_extents here, we can assume that all of
* that work has been done at higher layers, so this is truly the
* smallest the extent is going to get.
*/
spin_lock(&BTRFS_I(inode)->lock);
btrfs_mod_outstanding_extents(BTRFS_I(inode), 1);
spin_unlock(&BTRFS_I(inode)->lock);
return 0;
}
int btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
u64 start, u64 len, u64 disk_len, int type)
{
return __btrfs_add_ordered_extent(inode, file_offset, start, len,
disk_len, type, 0,
BTRFS_COMPRESS_NONE);
}
int btrfs_add_ordered_extent_dio(struct inode *inode, u64 file_offset,
u64 start, u64 len, u64 disk_len, int type)
{
return __btrfs_add_ordered_extent(inode, file_offset, start, len,
disk_len, type, 1,
BTRFS_COMPRESS_NONE);
}
int btrfs_add_ordered_extent_compress(struct inode *inode, u64 file_offset,
u64 start, u64 len, u64 disk_len,
int type, int compress_type)
{
return __btrfs_add_ordered_extent(inode, file_offset, start, len,
disk_len, type, 0,
compress_type);
}
/*
* Add a struct btrfs_ordered_sum into the list of checksums to be inserted
* when an ordered extent is finished. If the list covers more than one
* ordered extent, it is split across multiples.
*/
void btrfs_add_ordered_sum(struct btrfs_ordered_extent *entry,
struct btrfs_ordered_sum *sum)
{
struct btrfs_ordered_inode_tree *tree;
tree = &BTRFS_I(entry->inode)->ordered_tree;
spin_lock_irq(&tree->lock);
list_add_tail(&sum->list, &entry->list);
spin_unlock_irq(&tree->lock);
}
/*
* this is used to account for finished IO across a given range
* of the file. The IO may span ordered extents. If
* a given ordered_extent is completely done, 1 is returned, otherwise
* 0.
*
* test_and_set_bit on a flag in the struct btrfs_ordered_extent is used
* to make sure this function only returns 1 once for a given ordered extent.
*
* file_offset is updated to one byte past the range that is recorded as
* complete. This allows you to walk forward in the file.
*/
int btrfs_dec_test_first_ordered_pending(struct inode *inode,
struct btrfs_ordered_extent **cached,
u64 *file_offset, u64 io_size, int uptodate)
{
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
struct btrfs_ordered_inode_tree *tree;
struct rb_node *node;
struct btrfs_ordered_extent *entry = NULL;
int ret;
unsigned long flags;
u64 dec_end;
u64 dec_start;
u64 to_dec;
tree = &BTRFS_I(inode)->ordered_tree;
spin_lock_irqsave(&tree->lock, flags);
node = tree_search(tree, *file_offset);
if (!node) {
ret = 1;
goto out;
}
entry = rb_entry(node, struct btrfs_ordered_extent, rb_node);
if (!offset_in_entry(entry, *file_offset)) {
ret = 1;
goto out;
}
dec_start = max(*file_offset, entry->file_offset);
dec_end = min(*file_offset + io_size, entry->file_offset +
entry->len);
*file_offset = dec_end;
if (dec_start > dec_end) {
btrfs_crit(fs_info, "bad ordering dec_start %llu end %llu",
dec_start, dec_end);
}
to_dec = dec_end - dec_start;
if (to_dec > entry->bytes_left) {
btrfs_crit(fs_info,
"bad ordered accounting left %llu size %llu",
entry->bytes_left, to_dec);
}
entry->bytes_left -= to_dec;
if (!uptodate)
set_bit(BTRFS_ORDERED_IOERR, &entry->flags);
if (entry->bytes_left == 0) {
ret = test_and_set_bit(BTRFS_ORDERED_IO_DONE, &entry->flags);
/* test_and_set_bit implies a barrier */
cond_wake_up_nomb(&entry->wait);
} else {
ret = 1;
}
out:
if (!ret && cached && entry) {
*cached = entry;
refcount_inc(&entry->refs);
}
spin_unlock_irqrestore(&tree->lock, flags);
return ret == 0;
}
/*
* this is used to account for finished IO across a given range
* of the file. The IO should not span ordered extents. If
* a given ordered_extent is completely done, 1 is returned, otherwise
* 0.
*
* test_and_set_bit on a flag in the struct btrfs_ordered_extent is used
* to make sure this function only returns 1 once for a given ordered extent.
*/
int btrfs_dec_test_ordered_pending(struct inode *inode,
struct btrfs_ordered_extent **cached,
u64 file_offset, u64 io_size, int uptodate)
{
struct btrfs_ordered_inode_tree *tree;
struct rb_node *node;
struct btrfs_ordered_extent *entry = NULL;
unsigned long flags;
int ret;
tree = &BTRFS_I(inode)->ordered_tree;
spin_lock_irqsave(&tree->lock, flags);
if (cached && *cached) {
entry = *cached;
goto have_entry;
}
node = tree_search(tree, file_offset);
if (!node) {
ret = 1;
goto out;
}
entry = rb_entry(node, struct btrfs_ordered_extent, rb_node);
have_entry:
if (!offset_in_entry(entry, file_offset)) {
ret = 1;
goto out;
}
if (io_size > entry->bytes_left) {
btrfs_crit(BTRFS_I(inode)->root->fs_info,
"bad ordered accounting left %llu size %llu",
entry->bytes_left, io_size);
}
entry->bytes_left -= io_size;
if (!uptodate)
set_bit(BTRFS_ORDERED_IOERR, &entry->flags);
if (entry->bytes_left == 0) {
ret = test_and_set_bit(BTRFS_ORDERED_IO_DONE, &entry->flags);
/* test_and_set_bit implies a barrier */
cond_wake_up_nomb(&entry->wait);
} else {
ret = 1;
}
out:
if (!ret && cached && entry) {
*cached = entry;
refcount_inc(&entry->refs);
}
spin_unlock_irqrestore(&tree->lock, flags);
return ret == 0;
}
/*
* used to drop a reference on an ordered extent. This will free
* the extent if the last reference is dropped
*/
void btrfs_put_ordered_extent(struct btrfs_ordered_extent *entry)
{
struct list_head *cur;
struct btrfs_ordered_sum *sum;
Btrfs: add initial tracepoint support for btrfs Tracepoints can provide insight into why btrfs hits bugs and be greatly helpful for debugging, e.g dd-7822 [000] 2121.641088: btrfs_inode_request: root = 5(FS_TREE), gen = 4, ino = 256, blocks = 8, disk_i_size = 0, last_trans = 8, logged_trans = 0 dd-7822 [000] 2121.641100: btrfs_inode_new: root = 5(FS_TREE), gen = 8, ino = 257, blocks = 0, disk_i_size = 0, last_trans = 0, logged_trans = 0 btrfs-transacti-7804 [001] 2146.935420: btrfs_cow_block: root = 2(EXTENT_TREE), refs = 2, orig_buf = 29368320 (orig_level = 0), cow_buf = 29388800 (cow_level = 0) btrfs-transacti-7804 [001] 2146.935473: btrfs_cow_block: root = 1(ROOT_TREE), refs = 2, orig_buf = 29364224 (orig_level = 0), cow_buf = 29392896 (cow_level = 0) btrfs-transacti-7804 [001] 2146.972221: btrfs_transaction_commit: root = 1(ROOT_TREE), gen = 8 flush-btrfs-2-7821 [001] 2155.824210: btrfs_chunk_alloc: root = 3(CHUNK_TREE), offset = 1103101952, size = 1073741824, num_stripes = 1, sub_stripes = 0, type = DATA flush-btrfs-2-7821 [001] 2155.824241: btrfs_cow_block: root = 2(EXTENT_TREE), refs = 2, orig_buf = 29388800 (orig_level = 0), cow_buf = 29396992 (cow_level = 0) flush-btrfs-2-7821 [001] 2155.824255: btrfs_cow_block: root = 4(DEV_TREE), refs = 2, orig_buf = 29372416 (orig_level = 0), cow_buf = 29401088 (cow_level = 0) flush-btrfs-2-7821 [000] 2155.824329: btrfs_cow_block: root = 3(CHUNK_TREE), refs = 2, orig_buf = 20971520 (orig_level = 0), cow_buf = 20975616 (cow_level = 0) btrfs-endio-wri-7800 [001] 2155.898019: btrfs_cow_block: root = 5(FS_TREE), refs = 2, orig_buf = 29384704 (orig_level = 0), cow_buf = 29405184 (cow_level = 0) btrfs-endio-wri-7800 [001] 2155.898043: btrfs_cow_block: root = 7(CSUM_TREE), refs = 2, orig_buf = 29376512 (orig_level = 0), cow_buf = 29409280 (cow_level = 0) Here is what I have added: 1) ordere_extent: btrfs_ordered_extent_add btrfs_ordered_extent_remove btrfs_ordered_extent_start btrfs_ordered_extent_put These provide critical information to understand how ordered_extents are updated. 2) extent_map: btrfs_get_extent extent_map is used in both read and write cases, and it is useful for tracking how btrfs specific IO is running. 3) writepage: __extent_writepage btrfs_writepage_end_io_hook Pages are cirtical resourses and produce a lot of corner cases during writeback, so it is valuable to know how page is written to disk. 4) inode: btrfs_inode_new btrfs_inode_request btrfs_inode_evict These can show where and when a inode is created, when a inode is evicted. 5) sync: btrfs_sync_file btrfs_sync_fs These show sync arguments. 6) transaction: btrfs_transaction_commit In transaction based filesystem, it will be useful to know the generation and who does commit. 7) back reference and cow: btrfs_delayed_tree_ref btrfs_delayed_data_ref btrfs_delayed_ref_head btrfs_cow_block Btrfs natively supports back references, these tracepoints are helpful on understanding btrfs's COW mechanism. 8) chunk: btrfs_chunk_alloc btrfs_chunk_free Chunk is a link between physical offset and logical offset, and stands for space infomation in btrfs, and these are helpful on tracing space things. 9) reserved_extent: btrfs_reserved_extent_alloc btrfs_reserved_extent_free These can show how btrfs uses its space. Signed-off-by: Liu Bo <liubo2009@cn.fujitsu.com> Signed-off-by: Chris Mason <chris.mason@oracle.com>
2011-03-24 19:18:59 +08:00
trace_btrfs_ordered_extent_put(entry->inode, entry);
if (refcount_dec_and_test(&entry->refs)) {
Btrfs: fix memory corruption on failure to submit bio for direct IO If we fail to submit a bio for a direct IO request, we were grabbing the corresponding ordered extent and decrementing its reference count twice, once for our lookup reference and once for the ordered tree reference. This was a problem because it caused the ordered extent to be freed without removing it from the ordered tree and any lists it might be attached to, leaving dangling pointers to the ordered extent around. Example trace with CONFIG_DEBUG_PAGEALLOC=y: [161779.858707] BUG: unable to handle kernel paging request at 0000000087654330 [161779.859983] IP: [<ffffffff8124ca68>] rb_prev+0x22/0x3b [161779.860636] PGD 34d818067 PUD 0 [161779.860636] Oops: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC (...) [161779.860636] Call Trace: [161779.860636] [<ffffffffa06b36a6>] __tree_search+0xd9/0xf9 [btrfs] [161779.860636] [<ffffffffa06b3708>] tree_search+0x42/0x63 [btrfs] [161779.860636] [<ffffffffa06b4868>] ? btrfs_lookup_ordered_range+0x2d/0xa5 [btrfs] [161779.860636] [<ffffffffa06b4873>] btrfs_lookup_ordered_range+0x38/0xa5 [btrfs] [161779.860636] [<ffffffffa06aab8e>] btrfs_get_blocks_direct+0x11b/0x615 [btrfs] [161779.860636] [<ffffffff8119727f>] do_blockdev_direct_IO+0x5ff/0xb43 [161779.860636] [<ffffffffa06aaa73>] ? btrfs_page_exists_in_range+0x1ad/0x1ad [btrfs] [161779.860636] [<ffffffffa06a2c9a>] ? btrfs_get_extent_fiemap+0x1bc/0x1bc [btrfs] [161779.860636] [<ffffffff811977f5>] __blockdev_direct_IO+0x32/0x34 [161779.860636] [<ffffffffa06a2c9a>] ? btrfs_get_extent_fiemap+0x1bc/0x1bc [btrfs] [161779.860636] [<ffffffffa06a10ae>] btrfs_direct_IO+0x198/0x21f [btrfs] [161779.860636] [<ffffffffa06a2c9a>] ? btrfs_get_extent_fiemap+0x1bc/0x1bc [btrfs] [161779.860636] [<ffffffff81112ca1>] generic_file_direct_write+0xb3/0x128 [161779.860636] [<ffffffffa06affaa>] ? btrfs_file_write_iter+0x15f/0x3e0 [btrfs] [161779.860636] [<ffffffffa06b004c>] btrfs_file_write_iter+0x201/0x3e0 [btrfs] (...) We were also not freeing the btrfs_dio_private we allocated previously, which kmemleak reported with the following trace in its sysfs file: unreferenced object 0xffff8803f553bf80 (size 96): comm "xfs_io", pid 4501, jiffies 4295039588 (age 173.936s) hex dump (first 32 bytes): 88 6c 9b f5 02 88 ff ff 00 00 00 00 00 00 00 00 .l.............. 00 00 00 00 00 00 00 00 00 00 c4 00 00 00 00 00 ................ backtrace: [<ffffffff81161ffe>] create_object+0x172/0x29a [<ffffffff8145870f>] kmemleak_alloc+0x25/0x41 [<ffffffff81154e64>] kmemleak_alloc_recursive.constprop.40+0x16/0x18 [<ffffffff811579ed>] kmem_cache_alloc_trace+0xfb/0x148 [<ffffffffa03d8cff>] btrfs_submit_direct+0x65/0x16a [btrfs] [<ffffffff811968dc>] dio_bio_submit+0x62/0x8f [<ffffffff811975fe>] do_blockdev_direct_IO+0x97e/0xb43 [<ffffffff811977f5>] __blockdev_direct_IO+0x32/0x34 [<ffffffffa03d70ae>] btrfs_direct_IO+0x198/0x21f [btrfs] [<ffffffff81112ca1>] generic_file_direct_write+0xb3/0x128 [<ffffffffa03e604d>] btrfs_file_write_iter+0x201/0x3e0 [btrfs] [<ffffffff8116586a>] __vfs_write+0x7c/0xa5 [<ffffffff81165da9>] vfs_write+0xa0/0xe4 [<ffffffff81166675>] SyS_pwrite64+0x64/0x82 [<ffffffff81464fd7>] system_call_fastpath+0x12/0x6f [<ffffffffffffffff>] 0xffffffffffffffff For read requests we weren't doing any cleanup either (none of the work done by btrfs_endio_direct_read()), so a failure submitting a bio for a read request would leave a range in the inode's io_tree locked forever, blocking any future operations (both reads and writes) against that range. So fix this by making sure we do the same cleanup that we do for the case where the bio submission succeeds. Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Chris Mason <clm@fb.com>
2015-07-01 19:13:10 +08:00
ASSERT(list_empty(&entry->log_list));
ASSERT(list_empty(&entry->trans_list));
ASSERT(list_empty(&entry->root_extent_list));
ASSERT(RB_EMPTY_NODE(&entry->rb_node));
if (entry->inode)
btrfs_add_delayed_iput(entry->inode);
while (!list_empty(&entry->list)) {
cur = entry->list.next;
sum = list_entry(cur, struct btrfs_ordered_sum, list);
list_del(&sum->list);
kvfree(sum);
}
kmem_cache_free(btrfs_ordered_extent_cache, entry);
}
}
/*
* remove an ordered extent from the tree. No references are dropped
* and waiters are woken up.
*/
void btrfs_remove_ordered_extent(struct inode *inode,
struct btrfs_ordered_extent *entry)
{
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
struct btrfs_ordered_inode_tree *tree;
Btrfs: rework outstanding_extents Right now we do a lot of weird hoops around outstanding_extents in order to keep the extent count consistent. This is because we logically transfer the outstanding_extent count from the initial reservation through the set_delalloc_bits. This makes it pretty difficult to get a handle on how and when we need to mess with outstanding_extents. Fix this by revamping the rules of how we deal with outstanding_extents. Now instead everybody that is holding on to a delalloc extent is required to increase the outstanding extents count for itself. This means we'll have something like this btrfs_delalloc_reserve_metadata - outstanding_extents = 1 btrfs_set_extent_delalloc - outstanding_extents = 2 btrfs_release_delalloc_extents - outstanding_extents = 1 for an initial file write. Now take the append write where we extend an existing delalloc range but still under the maximum extent size btrfs_delalloc_reserve_metadata - outstanding_extents = 2 btrfs_set_extent_delalloc btrfs_set_bit_hook - outstanding_extents = 3 btrfs_merge_extent_hook - outstanding_extents = 2 btrfs_delalloc_release_extents - outstanding_extnets = 1 In order to make the ordered extent transition we of course must now make ordered extents carry their own outstanding_extent reservation, so for cow_file_range we end up with btrfs_add_ordered_extent - outstanding_extents = 2 clear_extent_bit - outstanding_extents = 1 btrfs_remove_ordered_extent - outstanding_extents = 0 This makes all manipulations of outstanding_extents much more explicit. Every successful call to btrfs_delalloc_reserve_metadata _must_ now be combined with btrfs_release_delalloc_extents, even in the error case, as that is the only function that actually modifies the outstanding_extents counter. The drawback to this is now we are much more likely to have transient cases where outstanding_extents is much larger than it actually should be. This could happen before as we manipulated the delalloc bits, but now it happens basically at every write. This may put more pressure on the ENOSPC flushing code, but I think making this code simpler is worth the cost. I have another change coming to mitigate this side-effect somewhat. I also added trace points for the counter manipulation. These were used by a bpf script I wrote to help track down leak issues. Signed-off-by: Josef Bacik <jbacik@fb.com> Signed-off-by: David Sterba <dsterba@suse.com>
2017-10-20 02:15:55 +08:00
struct btrfs_inode *btrfs_inode = BTRFS_I(inode);
struct btrfs_root *root = btrfs_inode->root;
struct rb_node *node;
Btrfs: rework outstanding_extents Right now we do a lot of weird hoops around outstanding_extents in order to keep the extent count consistent. This is because we logically transfer the outstanding_extent count from the initial reservation through the set_delalloc_bits. This makes it pretty difficult to get a handle on how and when we need to mess with outstanding_extents. Fix this by revamping the rules of how we deal with outstanding_extents. Now instead everybody that is holding on to a delalloc extent is required to increase the outstanding extents count for itself. This means we'll have something like this btrfs_delalloc_reserve_metadata - outstanding_extents = 1 btrfs_set_extent_delalloc - outstanding_extents = 2 btrfs_release_delalloc_extents - outstanding_extents = 1 for an initial file write. Now take the append write where we extend an existing delalloc range but still under the maximum extent size btrfs_delalloc_reserve_metadata - outstanding_extents = 2 btrfs_set_extent_delalloc btrfs_set_bit_hook - outstanding_extents = 3 btrfs_merge_extent_hook - outstanding_extents = 2 btrfs_delalloc_release_extents - outstanding_extnets = 1 In order to make the ordered extent transition we of course must now make ordered extents carry their own outstanding_extent reservation, so for cow_file_range we end up with btrfs_add_ordered_extent - outstanding_extents = 2 clear_extent_bit - outstanding_extents = 1 btrfs_remove_ordered_extent - outstanding_extents = 0 This makes all manipulations of outstanding_extents much more explicit. Every successful call to btrfs_delalloc_reserve_metadata _must_ now be combined with btrfs_release_delalloc_extents, even in the error case, as that is the only function that actually modifies the outstanding_extents counter. The drawback to this is now we are much more likely to have transient cases where outstanding_extents is much larger than it actually should be. This could happen before as we manipulated the delalloc bits, but now it happens basically at every write. This may put more pressure on the ENOSPC flushing code, but I think making this code simpler is worth the cost. I have another change coming to mitigate this side-effect somewhat. I also added trace points for the counter manipulation. These were used by a bpf script I wrote to help track down leak issues. Signed-off-by: Josef Bacik <jbacik@fb.com> Signed-off-by: David Sterba <dsterba@suse.com>
2017-10-20 02:15:55 +08:00
/* This is paired with btrfs_add_ordered_extent. */
spin_lock(&btrfs_inode->lock);
btrfs_mod_outstanding_extents(btrfs_inode, -1);
spin_unlock(&btrfs_inode->lock);
if (root != fs_info->tree_root)
btrfs: qgroup: Use separate meta reservation type for delalloc Before this patch, btrfs qgroup is mixing per-transcation meta rsv with preallocated meta rsv, making it quite easy to underflow qgroup meta reservation. Since we have the new qgroup meta rsv types, apply it to delalloc reservation. Now for delalloc, most of its reserved space will use META_PREALLOC qgroup rsv type. And for callers reducing outstanding extent like btrfs_finish_ordered_io(), they will convert corresponding META_PREALLOC reservation to META_PERTRANS. This is mainly due to the fact that current qgroup numbers will only be updated in btrfs_commit_transaction(), that's to say if we don't keep such placeholder reservation, we can exceed qgroup limitation. And for callers freeing outstanding extent in error handler, we will just free META_PREALLOC bytes. This behavior makes callers of btrfs_qgroup_release_meta() or btrfs_qgroup_convert_meta() to be aware of which type they are. So in this patch, btrfs_delalloc_release_metadata() and its callers get an extra parameter to info qgroup to do correct meta convert/release. The good news is, even we use the wrong type (convert or free), it won't cause obvious bug, as prealloc type is always in good shape, and the type only affects how per-trans meta is increased or not. So the worst case will be at most metadata limitation can be sometimes exceeded (no convert at all) or metadata limitation is reached too soon (no free at all). Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2017-12-12 15:34:32 +08:00
btrfs_delalloc_release_metadata(btrfs_inode, entry->len, false);
Btrfs: rework outstanding_extents Right now we do a lot of weird hoops around outstanding_extents in order to keep the extent count consistent. This is because we logically transfer the outstanding_extent count from the initial reservation through the set_delalloc_bits. This makes it pretty difficult to get a handle on how and when we need to mess with outstanding_extents. Fix this by revamping the rules of how we deal with outstanding_extents. Now instead everybody that is holding on to a delalloc extent is required to increase the outstanding extents count for itself. This means we'll have something like this btrfs_delalloc_reserve_metadata - outstanding_extents = 1 btrfs_set_extent_delalloc - outstanding_extents = 2 btrfs_release_delalloc_extents - outstanding_extents = 1 for an initial file write. Now take the append write where we extend an existing delalloc range but still under the maximum extent size btrfs_delalloc_reserve_metadata - outstanding_extents = 2 btrfs_set_extent_delalloc btrfs_set_bit_hook - outstanding_extents = 3 btrfs_merge_extent_hook - outstanding_extents = 2 btrfs_delalloc_release_extents - outstanding_extnets = 1 In order to make the ordered extent transition we of course must now make ordered extents carry their own outstanding_extent reservation, so for cow_file_range we end up with btrfs_add_ordered_extent - outstanding_extents = 2 clear_extent_bit - outstanding_extents = 1 btrfs_remove_ordered_extent - outstanding_extents = 0 This makes all manipulations of outstanding_extents much more explicit. Every successful call to btrfs_delalloc_reserve_metadata _must_ now be combined with btrfs_release_delalloc_extents, even in the error case, as that is the only function that actually modifies the outstanding_extents counter. The drawback to this is now we are much more likely to have transient cases where outstanding_extents is much larger than it actually should be. This could happen before as we manipulated the delalloc bits, but now it happens basically at every write. This may put more pressure on the ENOSPC flushing code, but I think making this code simpler is worth the cost. I have another change coming to mitigate this side-effect somewhat. I also added trace points for the counter manipulation. These were used by a bpf script I wrote to help track down leak issues. Signed-off-by: Josef Bacik <jbacik@fb.com> Signed-off-by: David Sterba <dsterba@suse.com>
2017-10-20 02:15:55 +08:00
if (test_bit(BTRFS_ORDERED_DIRECT, &entry->flags))
percpu_counter_add_batch(&fs_info->dio_bytes, -entry->len,
fs_info->delalloc_batch);
Btrfs: rework outstanding_extents Right now we do a lot of weird hoops around outstanding_extents in order to keep the extent count consistent. This is because we logically transfer the outstanding_extent count from the initial reservation through the set_delalloc_bits. This makes it pretty difficult to get a handle on how and when we need to mess with outstanding_extents. Fix this by revamping the rules of how we deal with outstanding_extents. Now instead everybody that is holding on to a delalloc extent is required to increase the outstanding extents count for itself. This means we'll have something like this btrfs_delalloc_reserve_metadata - outstanding_extents = 1 btrfs_set_extent_delalloc - outstanding_extents = 2 btrfs_release_delalloc_extents - outstanding_extents = 1 for an initial file write. Now take the append write where we extend an existing delalloc range but still under the maximum extent size btrfs_delalloc_reserve_metadata - outstanding_extents = 2 btrfs_set_extent_delalloc btrfs_set_bit_hook - outstanding_extents = 3 btrfs_merge_extent_hook - outstanding_extents = 2 btrfs_delalloc_release_extents - outstanding_extnets = 1 In order to make the ordered extent transition we of course must now make ordered extents carry their own outstanding_extent reservation, so for cow_file_range we end up with btrfs_add_ordered_extent - outstanding_extents = 2 clear_extent_bit - outstanding_extents = 1 btrfs_remove_ordered_extent - outstanding_extents = 0 This makes all manipulations of outstanding_extents much more explicit. Every successful call to btrfs_delalloc_reserve_metadata _must_ now be combined with btrfs_release_delalloc_extents, even in the error case, as that is the only function that actually modifies the outstanding_extents counter. The drawback to this is now we are much more likely to have transient cases where outstanding_extents is much larger than it actually should be. This could happen before as we manipulated the delalloc bits, but now it happens basically at every write. This may put more pressure on the ENOSPC flushing code, but I think making this code simpler is worth the cost. I have another change coming to mitigate this side-effect somewhat. I also added trace points for the counter manipulation. These were used by a bpf script I wrote to help track down leak issues. Signed-off-by: Josef Bacik <jbacik@fb.com> Signed-off-by: David Sterba <dsterba@suse.com>
2017-10-20 02:15:55 +08:00
tree = &btrfs_inode->ordered_tree;
spin_lock_irq(&tree->lock);
node = &entry->rb_node;
rb_erase(node, &tree->tree);
Btrfs: fix memory corruption on failure to submit bio for direct IO If we fail to submit a bio for a direct IO request, we were grabbing the corresponding ordered extent and decrementing its reference count twice, once for our lookup reference and once for the ordered tree reference. This was a problem because it caused the ordered extent to be freed without removing it from the ordered tree and any lists it might be attached to, leaving dangling pointers to the ordered extent around. Example trace with CONFIG_DEBUG_PAGEALLOC=y: [161779.858707] BUG: unable to handle kernel paging request at 0000000087654330 [161779.859983] IP: [<ffffffff8124ca68>] rb_prev+0x22/0x3b [161779.860636] PGD 34d818067 PUD 0 [161779.860636] Oops: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC (...) [161779.860636] Call Trace: [161779.860636] [<ffffffffa06b36a6>] __tree_search+0xd9/0xf9 [btrfs] [161779.860636] [<ffffffffa06b3708>] tree_search+0x42/0x63 [btrfs] [161779.860636] [<ffffffffa06b4868>] ? btrfs_lookup_ordered_range+0x2d/0xa5 [btrfs] [161779.860636] [<ffffffffa06b4873>] btrfs_lookup_ordered_range+0x38/0xa5 [btrfs] [161779.860636] [<ffffffffa06aab8e>] btrfs_get_blocks_direct+0x11b/0x615 [btrfs] [161779.860636] [<ffffffff8119727f>] do_blockdev_direct_IO+0x5ff/0xb43 [161779.860636] [<ffffffffa06aaa73>] ? btrfs_page_exists_in_range+0x1ad/0x1ad [btrfs] [161779.860636] [<ffffffffa06a2c9a>] ? btrfs_get_extent_fiemap+0x1bc/0x1bc [btrfs] [161779.860636] [<ffffffff811977f5>] __blockdev_direct_IO+0x32/0x34 [161779.860636] [<ffffffffa06a2c9a>] ? btrfs_get_extent_fiemap+0x1bc/0x1bc [btrfs] [161779.860636] [<ffffffffa06a10ae>] btrfs_direct_IO+0x198/0x21f [btrfs] [161779.860636] [<ffffffffa06a2c9a>] ? btrfs_get_extent_fiemap+0x1bc/0x1bc [btrfs] [161779.860636] [<ffffffff81112ca1>] generic_file_direct_write+0xb3/0x128 [161779.860636] [<ffffffffa06affaa>] ? btrfs_file_write_iter+0x15f/0x3e0 [btrfs] [161779.860636] [<ffffffffa06b004c>] btrfs_file_write_iter+0x201/0x3e0 [btrfs] (...) We were also not freeing the btrfs_dio_private we allocated previously, which kmemleak reported with the following trace in its sysfs file: unreferenced object 0xffff8803f553bf80 (size 96): comm "xfs_io", pid 4501, jiffies 4295039588 (age 173.936s) hex dump (first 32 bytes): 88 6c 9b f5 02 88 ff ff 00 00 00 00 00 00 00 00 .l.............. 00 00 00 00 00 00 00 00 00 00 c4 00 00 00 00 00 ................ backtrace: [<ffffffff81161ffe>] create_object+0x172/0x29a [<ffffffff8145870f>] kmemleak_alloc+0x25/0x41 [<ffffffff81154e64>] kmemleak_alloc_recursive.constprop.40+0x16/0x18 [<ffffffff811579ed>] kmem_cache_alloc_trace+0xfb/0x148 [<ffffffffa03d8cff>] btrfs_submit_direct+0x65/0x16a [btrfs] [<ffffffff811968dc>] dio_bio_submit+0x62/0x8f [<ffffffff811975fe>] do_blockdev_direct_IO+0x97e/0xb43 [<ffffffff811977f5>] __blockdev_direct_IO+0x32/0x34 [<ffffffffa03d70ae>] btrfs_direct_IO+0x198/0x21f [btrfs] [<ffffffff81112ca1>] generic_file_direct_write+0xb3/0x128 [<ffffffffa03e604d>] btrfs_file_write_iter+0x201/0x3e0 [btrfs] [<ffffffff8116586a>] __vfs_write+0x7c/0xa5 [<ffffffff81165da9>] vfs_write+0xa0/0xe4 [<ffffffff81166675>] SyS_pwrite64+0x64/0x82 [<ffffffff81464fd7>] system_call_fastpath+0x12/0x6f [<ffffffffffffffff>] 0xffffffffffffffff For read requests we weren't doing any cleanup either (none of the work done by btrfs_endio_direct_read()), so a failure submitting a bio for a read request would leave a range in the inode's io_tree locked forever, blocking any future operations (both reads and writes) against that range. So fix this by making sure we do the same cleanup that we do for the case where the bio submission succeeds. Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Chris Mason <clm@fb.com>
2015-07-01 19:13:10 +08:00
RB_CLEAR_NODE(node);
Btrfs: avoid unnecessary ordered extent cache resets After an ordered extent completes, don't blindly reset the inode's ordered tree last accessed ordered extent pointer. While running the xfstests I noticed that about 29% of the time the ordered extent to which tree->last pointed was not the same as our just completed ordered extent. After that I ran the following sysbench test (after a prepare phase) and noticed that about 68% of the time tree->last pointed to a different ordered extent too. sysbench --test=fileio --file-num=32 --file-total-size=4G \ --file-test-mode=rndwr --num-threads=512 \ --file-block-size=32768 --max-time=60 --max-requests=0 run Therefore reset tree->last on ordered extent removal only if it pointed to the ordered extent we're removing from the tree. Results from 4 runs of the following test before and after applying this patch: $ sysbench --test=fileio --file-num=32 --file-total-size=4G \ --file-test-mode=seqwr --num-threads=512 \ --file-block-size=32768 --max-time=60 --file-io-mode=sync prepare $ sysbench --test=fileio --file-num=32 --file-total-size=4G \ --file-test-mode=seqwr --num-threads=512 \ --file-block-size=32768 --max-time=60 --file-io-mode=sync run Before this path: run 1 - 64.049Mb/sec run 2 - 63.455Mb/sec run 3 - 64.656Mb/sec run 4 - 63.833Mb/sec After this patch: run 1 - 66.149Mb/sec run 2 - 68.459Mb/sec run 3 - 66.338Mb/sec run 4 - 66.176Mb/sec With random writes (--file-test-mode=rndwr) I had huge fluctuations on the results (+- 35% easily). Signed-off-by: Filipe David Borba Manana <fdmanana@gmail.com> Signed-off-by: Josef Bacik <jbacik@fb.com> Signed-off-by: Chris Mason <clm@fb.com>
2013-11-23 02:54:58 +08:00
if (tree->last == node)
tree->last = NULL;
set_bit(BTRFS_ORDERED_COMPLETE, &entry->flags);
spin_unlock_irq(&tree->lock);
spin_lock(&root->ordered_extent_lock);
list_del_init(&entry->root_extent_list);
root->nr_ordered_extents--;
Btrfs: add extra flushing for renames and truncates Renames and truncates are both common ways to replace old data with new data. The filesystem can make an effort to make sure the new data is on disk before actually replacing the old data. This is especially important for rename, which many application use as though it were atomic for both the data and the metadata involved. The current btrfs code will happily replace a file that is fully on disk with one that was just created and still has pending IO. If we crash after transaction commit but before the IO is done, we'll end up replacing a good file with a zero length file. The solution used here is to create a list of inodes that need special ordering and force them to disk before the commit is done. This is similar to the ext3 style data=ordering, except it is only done on selected files. Btrfs is able to get away with this because it does not wait on commits very often, even for fsync (which use a sub-commit). For renames, we order the file when it wasn't already on disk and when it is replacing an existing file. Larger files are sent to filemap_flush right away (before the transaction handle is opened). For truncates, we order if the file goes from non-zero size down to zero size. This is a little different, because at the time of the truncate the file has no dirty bytes to order. But, we flag the inode so that it is added to the ordered list on close (via release method). We also immediately add it to the ordered list of the current transaction so that we can try to flush down any writes the application sneaks in before commit. Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-04-01 01:27:11 +08:00
Btrfs: add initial tracepoint support for btrfs Tracepoints can provide insight into why btrfs hits bugs and be greatly helpful for debugging, e.g dd-7822 [000] 2121.641088: btrfs_inode_request: root = 5(FS_TREE), gen = 4, ino = 256, blocks = 8, disk_i_size = 0, last_trans = 8, logged_trans = 0 dd-7822 [000] 2121.641100: btrfs_inode_new: root = 5(FS_TREE), gen = 8, ino = 257, blocks = 0, disk_i_size = 0, last_trans = 0, logged_trans = 0 btrfs-transacti-7804 [001] 2146.935420: btrfs_cow_block: root = 2(EXTENT_TREE), refs = 2, orig_buf = 29368320 (orig_level = 0), cow_buf = 29388800 (cow_level = 0) btrfs-transacti-7804 [001] 2146.935473: btrfs_cow_block: root = 1(ROOT_TREE), refs = 2, orig_buf = 29364224 (orig_level = 0), cow_buf = 29392896 (cow_level = 0) btrfs-transacti-7804 [001] 2146.972221: btrfs_transaction_commit: root = 1(ROOT_TREE), gen = 8 flush-btrfs-2-7821 [001] 2155.824210: btrfs_chunk_alloc: root = 3(CHUNK_TREE), offset = 1103101952, size = 1073741824, num_stripes = 1, sub_stripes = 0, type = DATA flush-btrfs-2-7821 [001] 2155.824241: btrfs_cow_block: root = 2(EXTENT_TREE), refs = 2, orig_buf = 29388800 (orig_level = 0), cow_buf = 29396992 (cow_level = 0) flush-btrfs-2-7821 [001] 2155.824255: btrfs_cow_block: root = 4(DEV_TREE), refs = 2, orig_buf = 29372416 (orig_level = 0), cow_buf = 29401088 (cow_level = 0) flush-btrfs-2-7821 [000] 2155.824329: btrfs_cow_block: root = 3(CHUNK_TREE), refs = 2, orig_buf = 20971520 (orig_level = 0), cow_buf = 20975616 (cow_level = 0) btrfs-endio-wri-7800 [001] 2155.898019: btrfs_cow_block: root = 5(FS_TREE), refs = 2, orig_buf = 29384704 (orig_level = 0), cow_buf = 29405184 (cow_level = 0) btrfs-endio-wri-7800 [001] 2155.898043: btrfs_cow_block: root = 7(CSUM_TREE), refs = 2, orig_buf = 29376512 (orig_level = 0), cow_buf = 29409280 (cow_level = 0) Here is what I have added: 1) ordere_extent: btrfs_ordered_extent_add btrfs_ordered_extent_remove btrfs_ordered_extent_start btrfs_ordered_extent_put These provide critical information to understand how ordered_extents are updated. 2) extent_map: btrfs_get_extent extent_map is used in both read and write cases, and it is useful for tracking how btrfs specific IO is running. 3) writepage: __extent_writepage btrfs_writepage_end_io_hook Pages are cirtical resourses and produce a lot of corner cases during writeback, so it is valuable to know how page is written to disk. 4) inode: btrfs_inode_new btrfs_inode_request btrfs_inode_evict These can show where and when a inode is created, when a inode is evicted. 5) sync: btrfs_sync_file btrfs_sync_fs These show sync arguments. 6) transaction: btrfs_transaction_commit In transaction based filesystem, it will be useful to know the generation and who does commit. 7) back reference and cow: btrfs_delayed_tree_ref btrfs_delayed_data_ref btrfs_delayed_ref_head btrfs_cow_block Btrfs natively supports back references, these tracepoints are helpful on understanding btrfs's COW mechanism. 8) chunk: btrfs_chunk_alloc btrfs_chunk_free Chunk is a link between physical offset and logical offset, and stands for space infomation in btrfs, and these are helpful on tracing space things. 9) reserved_extent: btrfs_reserved_extent_alloc btrfs_reserved_extent_free These can show how btrfs uses its space. Signed-off-by: Liu Bo <liubo2009@cn.fujitsu.com> Signed-off-by: Chris Mason <chris.mason@oracle.com>
2011-03-24 19:18:59 +08:00
trace_btrfs_ordered_extent_remove(inode, entry);
if (!root->nr_ordered_extents) {
spin_lock(&fs_info->ordered_root_lock);
BUG_ON(list_empty(&root->ordered_root));
list_del_init(&root->ordered_root);
spin_unlock(&fs_info->ordered_root_lock);
}
spin_unlock(&root->ordered_extent_lock);
wake_up(&entry->wait);
}
static void btrfs_run_ordered_extent_work(struct btrfs_work *work)
{
struct btrfs_ordered_extent *ordered;
ordered = container_of(work, struct btrfs_ordered_extent, flush_work);
btrfs_start_ordered_extent(ordered->inode, ordered, 1);
complete(&ordered->completion);
}
/*
* wait for all the ordered extents in a root. This is done when balancing
* space between drives.
*/
u64 btrfs_wait_ordered_extents(struct btrfs_root *root, u64 nr,
const u64 range_start, const u64 range_len)
{
struct btrfs_fs_info *fs_info = root->fs_info;
LIST_HEAD(splice);
LIST_HEAD(skipped);
LIST_HEAD(works);
struct btrfs_ordered_extent *ordered, *next;
u64 count = 0;
const u64 range_end = range_start + range_len;
mutex_lock(&root->ordered_extent_mutex);
spin_lock(&root->ordered_extent_lock);
list_splice_init(&root->ordered_extents, &splice);
while (!list_empty(&splice) && nr) {
ordered = list_first_entry(&splice, struct btrfs_ordered_extent,
root_extent_list);
if (range_end <= ordered->start ||
ordered->start + ordered->disk_len <= range_start) {
list_move_tail(&ordered->root_extent_list, &skipped);
cond_resched_lock(&root->ordered_extent_lock);
continue;
}
list_move_tail(&ordered->root_extent_list,
&root->ordered_extents);
refcount_inc(&ordered->refs);
spin_unlock(&root->ordered_extent_lock);
btrfs_init_work(&ordered->flush_work,
Btrfs: fix task hang under heavy compressed write This has been reported and discussed for a long time, and this hang occurs in both 3.15 and 3.16. Btrfs now migrates to use kernel workqueue, but it introduces this hang problem. Btrfs has a kind of work queued as an ordered way, which means that its ordered_func() must be processed in the way of FIFO, so it usually looks like -- normal_work_helper(arg) work = container_of(arg, struct btrfs_work, normal_work); work->func() <---- (we name it work X) for ordered_work in wq->ordered_list ordered_work->ordered_func() ordered_work->ordered_free() The hang is a rare case, first when we find free space, we get an uncached block group, then we go to read its free space cache inode for free space information, so it will file a readahead request btrfs_readpages() for page that is not in page cache __do_readpage() submit_extent_page() btrfs_submit_bio_hook() btrfs_bio_wq_end_io() submit_bio() end_workqueue_bio() <--(ret by the 1st endio) queue a work(named work Y) for the 2nd also the real endio() So the hang occurs when work Y's work_struct and work X's work_struct happens to share the same address. A bit more explanation, A,B,C -- struct btrfs_work arg -- struct work_struct kthread: worker_thread() pick up a work_struct from @worklist process_one_work(arg) worker->current_work = arg; <-- arg is A->normal_work worker->current_func(arg) normal_work_helper(arg) A = container_of(arg, struct btrfs_work, normal_work); A->func() A->ordered_func() A->ordered_free() <-- A gets freed B->ordered_func() submit_compressed_extents() find_free_extent() load_free_space_inode() ... <-- (the above readhead stack) end_workqueue_bio() btrfs_queue_work(work C) B->ordered_free() As if work A has a high priority in wq->ordered_list and there are more ordered works queued after it, such as B->ordered_func(), its memory could have been freed before normal_work_helper() returns, which means that kernel workqueue code worker_thread() still has worker->current_work pointer to be work A->normal_work's, ie. arg's address. Meanwhile, work C is allocated after work A is freed, work C->normal_work and work A->normal_work are likely to share the same address(I confirmed this with ftrace output, so I'm not just guessing, it's rare though). When another kthread picks up work C->normal_work to process, and finds our kthread is processing it(see find_worker_executing_work()), it'll think work C as a collision and skip then, which ends up nobody processing work C. So the situation is that our kthread is waiting forever on work C. Besides, there're other cases that can lead to deadlock, but the real problem is that all btrfs workqueue shares one work->func, -- normal_work_helper, so this makes each workqueue to have its own helper function, but only a wraper pf normal_work_helper. With this patch, I no long hit the above hang. Signed-off-by: Liu Bo <bo.li.liu@oracle.com> Signed-off-by: Chris Mason <clm@fb.com>
2014-08-15 23:36:53 +08:00
btrfs_flush_delalloc_helper,
btrfs_run_ordered_extent_work, NULL, NULL);
list_add_tail(&ordered->work_list, &works);
btrfs_queue_work(fs_info->flush_workers, &ordered->flush_work);
cond_resched();
spin_lock(&root->ordered_extent_lock);
if (nr != U64_MAX)
nr--;
count++;
}
list_splice_tail(&skipped, &root->ordered_extents);
list_splice_tail(&splice, &root->ordered_extents);
spin_unlock(&root->ordered_extent_lock);
list_for_each_entry_safe(ordered, next, &works, work_list) {
list_del_init(&ordered->work_list);
wait_for_completion(&ordered->completion);
btrfs_put_ordered_extent(ordered);
cond_resched();
}
mutex_unlock(&root->ordered_extent_mutex);
return count;
}
u64 btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr,
const u64 range_start, const u64 range_len)
{
struct btrfs_root *root;
struct list_head splice;
u64 total_done = 0;
u64 done;
INIT_LIST_HEAD(&splice);
mutex_lock(&fs_info->ordered_operations_mutex);
spin_lock(&fs_info->ordered_root_lock);
list_splice_init(&fs_info->ordered_roots, &splice);
while (!list_empty(&splice) && nr) {
root = list_first_entry(&splice, struct btrfs_root,
ordered_root);
root = btrfs_grab_fs_root(root);
BUG_ON(!root);
list_move_tail(&root->ordered_root,
&fs_info->ordered_roots);
spin_unlock(&fs_info->ordered_root_lock);
done = btrfs_wait_ordered_extents(root, nr,
range_start, range_len);
btrfs_put_fs_root(root);
Btrfs: fix race setting block group readonly during device replace When we do a device replace, for each device extent we find from the source device, we set the corresponding block group to readonly mode to prevent writes into it from happening while we are copying the device extent from the source to the target device. However just before we set the block group to readonly mode some concurrent task might have already allocated an extent from it or decided it could perform a nocow write into one of its extents, which can make the device replace process to miss copying an extent since it uses the extent tree's commit root to search for extents and only once it finishes searching for all extents belonging to the block group it does set the left cursor to the logical end address of the block group - this is a problem if the respective ordered extents finish while we are searching for extents using the extent tree's commit root and no transaction commit happens while we are iterating the tree, since it's the delayed references created by the ordered extents (when they complete) that insert the extent items into the extent tree (using the non-commit root of course). Example: CPU 1 CPU 2 btrfs_dev_replace_start() btrfs_scrub_dev() scrub_enumerate_chunks() --> finds device extent belonging to block group X <transaction N starts> starts buffered write against some inode writepages is run against that inode forcing dellaloc to run btrfs_writepages() extent_writepages() extent_write_cache_pages() __extent_writepage() writepage_delalloc() run_delalloc_range() cow_file_range() btrfs_reserve_extent() --> allocates an extent from block group X (which is not yet in RO mode) btrfs_add_ordered_extent() --> creates ordered extent Y flush_epd_write_bio() --> bio against the extent from block group X is submitted btrfs_inc_block_group_ro(bg X) --> sets block group X to readonly scrub_chunk(bg X) scrub_stripe(device extent from srcdev) --> keeps searching for extent items belonging to the block group using the extent tree's commit root --> it never blocks due to fs_info->scrub_pause_req as no one tries to commit transaction N --> copies all extents found from the source device into the target device --> finishes search loop bio completes ordered extent Y completes and creates delayed data reference which will add an extent item to the extent tree when run (typically at transaction commit time) --> so the task doing the scrub/device replace at CPU 1 misses this and does not copy this extent into the new/target device btrfs_dec_block_group_ro(bg X) --> turns block group X back to RW mode dev_replace->cursor_left is set to the logical end offset of block group X So fix this by waiting for all cow and nocow writes after setting a block group to readonly mode. Signed-off-by: Filipe Manana <fdmanana@suse.com> Reviewed-by: Josef Bacik <jbacik@fb.com>
2016-05-14 16:12:53 +08:00
total_done += done;
spin_lock(&fs_info->ordered_root_lock);
if (nr != U64_MAX) {
nr -= done;
}
}
list_splice_tail(&splice, &fs_info->ordered_roots);
spin_unlock(&fs_info->ordered_root_lock);
mutex_unlock(&fs_info->ordered_operations_mutex);
Btrfs: fix race setting block group readonly during device replace When we do a device replace, for each device extent we find from the source device, we set the corresponding block group to readonly mode to prevent writes into it from happening while we are copying the device extent from the source to the target device. However just before we set the block group to readonly mode some concurrent task might have already allocated an extent from it or decided it could perform a nocow write into one of its extents, which can make the device replace process to miss copying an extent since it uses the extent tree's commit root to search for extents and only once it finishes searching for all extents belonging to the block group it does set the left cursor to the logical end address of the block group - this is a problem if the respective ordered extents finish while we are searching for extents using the extent tree's commit root and no transaction commit happens while we are iterating the tree, since it's the delayed references created by the ordered extents (when they complete) that insert the extent items into the extent tree (using the non-commit root of course). Example: CPU 1 CPU 2 btrfs_dev_replace_start() btrfs_scrub_dev() scrub_enumerate_chunks() --> finds device extent belonging to block group X <transaction N starts> starts buffered write against some inode writepages is run against that inode forcing dellaloc to run btrfs_writepages() extent_writepages() extent_write_cache_pages() __extent_writepage() writepage_delalloc() run_delalloc_range() cow_file_range() btrfs_reserve_extent() --> allocates an extent from block group X (which is not yet in RO mode) btrfs_add_ordered_extent() --> creates ordered extent Y flush_epd_write_bio() --> bio against the extent from block group X is submitted btrfs_inc_block_group_ro(bg X) --> sets block group X to readonly scrub_chunk(bg X) scrub_stripe(device extent from srcdev) --> keeps searching for extent items belonging to the block group using the extent tree's commit root --> it never blocks due to fs_info->scrub_pause_req as no one tries to commit transaction N --> copies all extents found from the source device into the target device --> finishes search loop bio completes ordered extent Y completes and creates delayed data reference which will add an extent item to the extent tree when run (typically at transaction commit time) --> so the task doing the scrub/device replace at CPU 1 misses this and does not copy this extent into the new/target device btrfs_dec_block_group_ro(bg X) --> turns block group X back to RW mode dev_replace->cursor_left is set to the logical end offset of block group X So fix this by waiting for all cow and nocow writes after setting a block group to readonly mode. Signed-off-by: Filipe Manana <fdmanana@suse.com> Reviewed-by: Josef Bacik <jbacik@fb.com>
2016-05-14 16:12:53 +08:00
return total_done;
}
/*
* Used to start IO or wait for a given ordered extent to finish.
*
* If wait is one, this effectively waits on page writeback for all the pages
* in the extent, and it waits on the io completion code to insert
* metadata into the btree corresponding to the extent
*/
void btrfs_start_ordered_extent(struct inode *inode,
struct btrfs_ordered_extent *entry,
int wait)
{
u64 start = entry->file_offset;
u64 end = start + entry->len - 1;
Btrfs: add initial tracepoint support for btrfs Tracepoints can provide insight into why btrfs hits bugs and be greatly helpful for debugging, e.g dd-7822 [000] 2121.641088: btrfs_inode_request: root = 5(FS_TREE), gen = 4, ino = 256, blocks = 8, disk_i_size = 0, last_trans = 8, logged_trans = 0 dd-7822 [000] 2121.641100: btrfs_inode_new: root = 5(FS_TREE), gen = 8, ino = 257, blocks = 0, disk_i_size = 0, last_trans = 0, logged_trans = 0 btrfs-transacti-7804 [001] 2146.935420: btrfs_cow_block: root = 2(EXTENT_TREE), refs = 2, orig_buf = 29368320 (orig_level = 0), cow_buf = 29388800 (cow_level = 0) btrfs-transacti-7804 [001] 2146.935473: btrfs_cow_block: root = 1(ROOT_TREE), refs = 2, orig_buf = 29364224 (orig_level = 0), cow_buf = 29392896 (cow_level = 0) btrfs-transacti-7804 [001] 2146.972221: btrfs_transaction_commit: root = 1(ROOT_TREE), gen = 8 flush-btrfs-2-7821 [001] 2155.824210: btrfs_chunk_alloc: root = 3(CHUNK_TREE), offset = 1103101952, size = 1073741824, num_stripes = 1, sub_stripes = 0, type = DATA flush-btrfs-2-7821 [001] 2155.824241: btrfs_cow_block: root = 2(EXTENT_TREE), refs = 2, orig_buf = 29388800 (orig_level = 0), cow_buf = 29396992 (cow_level = 0) flush-btrfs-2-7821 [001] 2155.824255: btrfs_cow_block: root = 4(DEV_TREE), refs = 2, orig_buf = 29372416 (orig_level = 0), cow_buf = 29401088 (cow_level = 0) flush-btrfs-2-7821 [000] 2155.824329: btrfs_cow_block: root = 3(CHUNK_TREE), refs = 2, orig_buf = 20971520 (orig_level = 0), cow_buf = 20975616 (cow_level = 0) btrfs-endio-wri-7800 [001] 2155.898019: btrfs_cow_block: root = 5(FS_TREE), refs = 2, orig_buf = 29384704 (orig_level = 0), cow_buf = 29405184 (cow_level = 0) btrfs-endio-wri-7800 [001] 2155.898043: btrfs_cow_block: root = 7(CSUM_TREE), refs = 2, orig_buf = 29376512 (orig_level = 0), cow_buf = 29409280 (cow_level = 0) Here is what I have added: 1) ordere_extent: btrfs_ordered_extent_add btrfs_ordered_extent_remove btrfs_ordered_extent_start btrfs_ordered_extent_put These provide critical information to understand how ordered_extents are updated. 2) extent_map: btrfs_get_extent extent_map is used in both read and write cases, and it is useful for tracking how btrfs specific IO is running. 3) writepage: __extent_writepage btrfs_writepage_end_io_hook Pages are cirtical resourses and produce a lot of corner cases during writeback, so it is valuable to know how page is written to disk. 4) inode: btrfs_inode_new btrfs_inode_request btrfs_inode_evict These can show where and when a inode is created, when a inode is evicted. 5) sync: btrfs_sync_file btrfs_sync_fs These show sync arguments. 6) transaction: btrfs_transaction_commit In transaction based filesystem, it will be useful to know the generation and who does commit. 7) back reference and cow: btrfs_delayed_tree_ref btrfs_delayed_data_ref btrfs_delayed_ref_head btrfs_cow_block Btrfs natively supports back references, these tracepoints are helpful on understanding btrfs's COW mechanism. 8) chunk: btrfs_chunk_alloc btrfs_chunk_free Chunk is a link between physical offset and logical offset, and stands for space infomation in btrfs, and these are helpful on tracing space things. 9) reserved_extent: btrfs_reserved_extent_alloc btrfs_reserved_extent_free These can show how btrfs uses its space. Signed-off-by: Liu Bo <liubo2009@cn.fujitsu.com> Signed-off-by: Chris Mason <chris.mason@oracle.com>
2011-03-24 19:18:59 +08:00
trace_btrfs_ordered_extent_start(inode, entry);
/*
* pages in the range can be dirty, clean or writeback. We
* start IO on any dirty ones so the wait doesn't stall waiting
* for the flusher thread to find them
*/
if (!test_bit(BTRFS_ORDERED_DIRECT, &entry->flags))
filemap_fdatawrite_range(inode->i_mapping, start, end);
Btrfs: Add zlib compression support This is a large change for adding compression on reading and writing, both for inline and regular extents. It does some fairly large surgery to the writeback paths. Compression is off by default and enabled by mount -o compress. Even when the -o compress mount option is not used, it is possible to read compressed extents off the disk. If compression for a given set of pages fails to make them smaller, the file is flagged to avoid future compression attempts later. * While finding delalloc extents, the pages are locked before being sent down to the delalloc handler. This allows the delalloc handler to do complex things such as cleaning the pages, marking them writeback and starting IO on their behalf. * Inline extents are inserted at delalloc time now. This allows us to compress the data before inserting the inline extent, and it allows us to insert an inline extent that spans multiple pages. * All of the in-memory extent representations (extent_map.c, ordered-data.c etc) are changed to record both an in-memory size and an on disk size, as well as a flag for compression. From a disk format point of view, the extent pointers in the file are changed to record the on disk size of a given extent and some encoding flags. Space in the disk format is allocated for compression encoding, as well as encryption and a generic 'other' field. Neither the encryption or the 'other' field are currently used. In order to limit the amount of data read for a single random read in the file, the size of a compressed extent is limited to 128k. This is a software only limit, the disk format supports u64 sized compressed extents. In order to limit the ram consumed while processing extents, the uncompressed size of a compressed extent is limited to 256k. This is a software only limit and will be subject to tuning later. Checksumming is still done on compressed extents, and it is done on the uncompressed version of the data. This way additional encodings can be layered on without having to figure out which encoding to checksum. Compression happens at delalloc time, which is basically singled threaded because it is usually done by a single pdflush thread. This makes it tricky to spread the compression load across all the cpus on the box. We'll have to look at parallel pdflush walks of dirty inodes at a later time. Decompression is hooked into readpages and it does spread across CPUs nicely. Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-10-30 02:49:59 +08:00
if (wait) {
wait_event(entry->wait, test_bit(BTRFS_ORDERED_COMPLETE,
&entry->flags));
Btrfs: Add zlib compression support This is a large change for adding compression on reading and writing, both for inline and regular extents. It does some fairly large surgery to the writeback paths. Compression is off by default and enabled by mount -o compress. Even when the -o compress mount option is not used, it is possible to read compressed extents off the disk. If compression for a given set of pages fails to make them smaller, the file is flagged to avoid future compression attempts later. * While finding delalloc extents, the pages are locked before being sent down to the delalloc handler. This allows the delalloc handler to do complex things such as cleaning the pages, marking them writeback and starting IO on their behalf. * Inline extents are inserted at delalloc time now. This allows us to compress the data before inserting the inline extent, and it allows us to insert an inline extent that spans multiple pages. * All of the in-memory extent representations (extent_map.c, ordered-data.c etc) are changed to record both an in-memory size and an on disk size, as well as a flag for compression. From a disk format point of view, the extent pointers in the file are changed to record the on disk size of a given extent and some encoding flags. Space in the disk format is allocated for compression encoding, as well as encryption and a generic 'other' field. Neither the encryption or the 'other' field are currently used. In order to limit the amount of data read for a single random read in the file, the size of a compressed extent is limited to 128k. This is a software only limit, the disk format supports u64 sized compressed extents. In order to limit the ram consumed while processing extents, the uncompressed size of a compressed extent is limited to 256k. This is a software only limit and will be subject to tuning later. Checksumming is still done on compressed extents, and it is done on the uncompressed version of the data. This way additional encodings can be layered on without having to figure out which encoding to checksum. Compression happens at delalloc time, which is basically singled threaded because it is usually done by a single pdflush thread. This makes it tricky to spread the compression load across all the cpus on the box. We'll have to look at parallel pdflush walks of dirty inodes at a later time. Decompression is hooked into readpages and it does spread across CPUs nicely. Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-10-30 02:49:59 +08:00
}
}
/*
* Used to wait on ordered extents across a large range of bytes.
*/
int btrfs_wait_ordered_range(struct inode *inode, u64 start, u64 len)
{
int ret = 0;
Btrfs: fix panic when starting bg cache writeout after IO error When waiting for the writeback of block group cache we returned immediately if there was an error during writeback without waiting for the ordered extent to complete. This left a short time window where if some other task attempts to start the writeout for the same block group cache it can attempt to add a new ordered extent, starting at the same offset (0) before the previous one is removed from the ordered tree, causing an ordered tree panic (calls BUG()). This normally doesn't happen in other write paths, such as buffered writes or direct IO writes for regular files, since before marking page ranges dirty we lock the ranges and wait for any ordered extents within the range to complete first. Fix this by making btrfs_wait_ordered_range() not return immediately if it gets an error from the writeback, waiting for all ordered extents to complete first. This issue happened often when running the fstest btrfs/088 and it's easy to trigger it by running in a loop until the panic happens: for ((i = 1; i <= 10000; i++)) do ./check btrfs/088 ; done [17156.862573] BTRFS critical (device sdc): panic in ordered_data_tree_panic:70: Inconsistency in ordered tree at offset 0 (errno=-17 Object already exists) [17156.864052] ------------[ cut here ]------------ [17156.864052] kernel BUG at fs/btrfs/ordered-data.c:70! (...) [17156.864052] Call Trace: [17156.864052] [<ffffffffa03876e3>] btrfs_add_ordered_extent+0x12/0x14 [btrfs] [17156.864052] [<ffffffffa03787e2>] run_delalloc_nocow+0x5bf/0x747 [btrfs] [17156.864052] [<ffffffffa03789ff>] run_delalloc_range+0x95/0x353 [btrfs] [17156.864052] [<ffffffffa038b7fe>] writepage_delalloc.isra.16+0xb9/0x13f [btrfs] [17156.864052] [<ffffffffa038d75b>] __extent_writepage+0x129/0x1f7 [btrfs] [17156.864052] [<ffffffffa038da5a>] extent_write_cache_pages.isra.15.constprop.28+0x231/0x2f4 [btrfs] [17156.864052] [<ffffffff810ad2af>] ? __module_text_address+0x12/0x59 [17156.864052] [<ffffffff8107d33d>] ? trace_hardirqs_on+0xd/0xf [17156.864052] [<ffffffffa038df76>] extent_writepages+0x4b/0x5c [btrfs] [17156.864052] [<ffffffff81144431>] ? kmem_cache_free+0x9b/0xce [17156.864052] [<ffffffffa0376a46>] ? btrfs_submit_direct+0x3fc/0x3fc [btrfs] [17156.864052] [<ffffffffa0389cd6>] ? free_extent_state+0x8c/0xc1 [btrfs] [17156.864052] [<ffffffffa0374871>] btrfs_writepages+0x28/0x2a [btrfs] [17156.864052] [<ffffffff8110c4c8>] do_writepages+0x23/0x2c [17156.864052] [<ffffffff81102f36>] __filemap_fdatawrite_range+0x5a/0x61 [17156.864052] [<ffffffff81102f6e>] filemap_fdatawrite_range+0x13/0x15 [17156.864052] [<ffffffffa0383ef7>] btrfs_fdatawrite_range+0x21/0x48 [btrfs] [17156.864052] [<ffffffffa03ab89e>] __btrfs_write_out_cache.isra.14+0x2d9/0x3a7 [btrfs] [17156.864052] [<ffffffffa03ac1ab>] ? btrfs_write_out_cache+0x41/0xdc [btrfs] [17156.864052] [<ffffffffa03ac1fd>] btrfs_write_out_cache+0x93/0xdc [btrfs] [17156.864052] [<ffffffffa0363847>] ? btrfs_start_dirty_block_groups+0x13a/0x2b2 [btrfs] [17156.864052] [<ffffffffa03638e6>] btrfs_start_dirty_block_groups+0x1d9/0x2b2 [btrfs] [17156.864052] [<ffffffff8107d33d>] ? trace_hardirqs_on+0xd/0xf [17156.864052] [<ffffffffa037209e>] btrfs_commit_transaction+0x130/0x9c9 [btrfs] [17156.864052] [<ffffffffa034c748>] btrfs_sync_fs+0xe1/0x12d [btrfs] Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Chris Mason <clm@fb.com>
2015-05-06 02:03:10 +08:00
int ret_wb = 0;
u64 end;
u64 orig_end;
struct btrfs_ordered_extent *ordered;
if (start + len < start) {
orig_end = INT_LIMIT(loff_t);
} else {
orig_end = start + len - 1;
if (orig_end > INT_LIMIT(loff_t))
orig_end = INT_LIMIT(loff_t);
}
/* start IO across the range first to instantiate any delalloc
* extents
*/
ret = btrfs_fdatawrite_range(inode, start, orig_end);
if (ret)
return ret;
Btrfs: fix panic when starting bg cache writeout after IO error When waiting for the writeback of block group cache we returned immediately if there was an error during writeback without waiting for the ordered extent to complete. This left a short time window where if some other task attempts to start the writeout for the same block group cache it can attempt to add a new ordered extent, starting at the same offset (0) before the previous one is removed from the ordered tree, causing an ordered tree panic (calls BUG()). This normally doesn't happen in other write paths, such as buffered writes or direct IO writes for regular files, since before marking page ranges dirty we lock the ranges and wait for any ordered extents within the range to complete first. Fix this by making btrfs_wait_ordered_range() not return immediately if it gets an error from the writeback, waiting for all ordered extents to complete first. This issue happened often when running the fstest btrfs/088 and it's easy to trigger it by running in a loop until the panic happens: for ((i = 1; i <= 10000; i++)) do ./check btrfs/088 ; done [17156.862573] BTRFS critical (device sdc): panic in ordered_data_tree_panic:70: Inconsistency in ordered tree at offset 0 (errno=-17 Object already exists) [17156.864052] ------------[ cut here ]------------ [17156.864052] kernel BUG at fs/btrfs/ordered-data.c:70! (...) [17156.864052] Call Trace: [17156.864052] [<ffffffffa03876e3>] btrfs_add_ordered_extent+0x12/0x14 [btrfs] [17156.864052] [<ffffffffa03787e2>] run_delalloc_nocow+0x5bf/0x747 [btrfs] [17156.864052] [<ffffffffa03789ff>] run_delalloc_range+0x95/0x353 [btrfs] [17156.864052] [<ffffffffa038b7fe>] writepage_delalloc.isra.16+0xb9/0x13f [btrfs] [17156.864052] [<ffffffffa038d75b>] __extent_writepage+0x129/0x1f7 [btrfs] [17156.864052] [<ffffffffa038da5a>] extent_write_cache_pages.isra.15.constprop.28+0x231/0x2f4 [btrfs] [17156.864052] [<ffffffff810ad2af>] ? __module_text_address+0x12/0x59 [17156.864052] [<ffffffff8107d33d>] ? trace_hardirqs_on+0xd/0xf [17156.864052] [<ffffffffa038df76>] extent_writepages+0x4b/0x5c [btrfs] [17156.864052] [<ffffffff81144431>] ? kmem_cache_free+0x9b/0xce [17156.864052] [<ffffffffa0376a46>] ? btrfs_submit_direct+0x3fc/0x3fc [btrfs] [17156.864052] [<ffffffffa0389cd6>] ? free_extent_state+0x8c/0xc1 [btrfs] [17156.864052] [<ffffffffa0374871>] btrfs_writepages+0x28/0x2a [btrfs] [17156.864052] [<ffffffff8110c4c8>] do_writepages+0x23/0x2c [17156.864052] [<ffffffff81102f36>] __filemap_fdatawrite_range+0x5a/0x61 [17156.864052] [<ffffffff81102f6e>] filemap_fdatawrite_range+0x13/0x15 [17156.864052] [<ffffffffa0383ef7>] btrfs_fdatawrite_range+0x21/0x48 [btrfs] [17156.864052] [<ffffffffa03ab89e>] __btrfs_write_out_cache.isra.14+0x2d9/0x3a7 [btrfs] [17156.864052] [<ffffffffa03ac1ab>] ? btrfs_write_out_cache+0x41/0xdc [btrfs] [17156.864052] [<ffffffffa03ac1fd>] btrfs_write_out_cache+0x93/0xdc [btrfs] [17156.864052] [<ffffffffa0363847>] ? btrfs_start_dirty_block_groups+0x13a/0x2b2 [btrfs] [17156.864052] [<ffffffffa03638e6>] btrfs_start_dirty_block_groups+0x1d9/0x2b2 [btrfs] [17156.864052] [<ffffffff8107d33d>] ? trace_hardirqs_on+0xd/0xf [17156.864052] [<ffffffffa037209e>] btrfs_commit_transaction+0x130/0x9c9 [btrfs] [17156.864052] [<ffffffffa034c748>] btrfs_sync_fs+0xe1/0x12d [btrfs] Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Chris Mason <clm@fb.com>
2015-05-06 02:03:10 +08:00
/*
* If we have a writeback error don't return immediately. Wait first
* for any ordered extents that haven't completed yet. This is to make
* sure no one can dirty the same page ranges and call writepages()
* before the ordered extents complete - to avoid failures (-EEXIST)
* when adding the new ordered extents to the ordered tree.
*/
ret_wb = filemap_fdatawait_range(inode->i_mapping, start, orig_end);
end = orig_end;
while (1) {
ordered = btrfs_lookup_first_ordered_extent(inode, end);
if (!ordered)
break;
if (ordered->file_offset > orig_end) {
btrfs_put_ordered_extent(ordered);
break;
}
if (ordered->file_offset + ordered->len <= start) {
btrfs_put_ordered_extent(ordered);
break;
}
btrfs_start_ordered_extent(inode, ordered, 1);
end = ordered->file_offset;
if (test_bit(BTRFS_ORDERED_IOERR, &ordered->flags))
ret = -EIO;
btrfs_put_ordered_extent(ordered);
if (ret || end == 0 || end == start)
break;
end--;
}
Btrfs: fix panic when starting bg cache writeout after IO error When waiting for the writeback of block group cache we returned immediately if there was an error during writeback without waiting for the ordered extent to complete. This left a short time window where if some other task attempts to start the writeout for the same block group cache it can attempt to add a new ordered extent, starting at the same offset (0) before the previous one is removed from the ordered tree, causing an ordered tree panic (calls BUG()). This normally doesn't happen in other write paths, such as buffered writes or direct IO writes for regular files, since before marking page ranges dirty we lock the ranges and wait for any ordered extents within the range to complete first. Fix this by making btrfs_wait_ordered_range() not return immediately if it gets an error from the writeback, waiting for all ordered extents to complete first. This issue happened often when running the fstest btrfs/088 and it's easy to trigger it by running in a loop until the panic happens: for ((i = 1; i <= 10000; i++)) do ./check btrfs/088 ; done [17156.862573] BTRFS critical (device sdc): panic in ordered_data_tree_panic:70: Inconsistency in ordered tree at offset 0 (errno=-17 Object already exists) [17156.864052] ------------[ cut here ]------------ [17156.864052] kernel BUG at fs/btrfs/ordered-data.c:70! (...) [17156.864052] Call Trace: [17156.864052] [<ffffffffa03876e3>] btrfs_add_ordered_extent+0x12/0x14 [btrfs] [17156.864052] [<ffffffffa03787e2>] run_delalloc_nocow+0x5bf/0x747 [btrfs] [17156.864052] [<ffffffffa03789ff>] run_delalloc_range+0x95/0x353 [btrfs] [17156.864052] [<ffffffffa038b7fe>] writepage_delalloc.isra.16+0xb9/0x13f [btrfs] [17156.864052] [<ffffffffa038d75b>] __extent_writepage+0x129/0x1f7 [btrfs] [17156.864052] [<ffffffffa038da5a>] extent_write_cache_pages.isra.15.constprop.28+0x231/0x2f4 [btrfs] [17156.864052] [<ffffffff810ad2af>] ? __module_text_address+0x12/0x59 [17156.864052] [<ffffffff8107d33d>] ? trace_hardirqs_on+0xd/0xf [17156.864052] [<ffffffffa038df76>] extent_writepages+0x4b/0x5c [btrfs] [17156.864052] [<ffffffff81144431>] ? kmem_cache_free+0x9b/0xce [17156.864052] [<ffffffffa0376a46>] ? btrfs_submit_direct+0x3fc/0x3fc [btrfs] [17156.864052] [<ffffffffa0389cd6>] ? free_extent_state+0x8c/0xc1 [btrfs] [17156.864052] [<ffffffffa0374871>] btrfs_writepages+0x28/0x2a [btrfs] [17156.864052] [<ffffffff8110c4c8>] do_writepages+0x23/0x2c [17156.864052] [<ffffffff81102f36>] __filemap_fdatawrite_range+0x5a/0x61 [17156.864052] [<ffffffff81102f6e>] filemap_fdatawrite_range+0x13/0x15 [17156.864052] [<ffffffffa0383ef7>] btrfs_fdatawrite_range+0x21/0x48 [btrfs] [17156.864052] [<ffffffffa03ab89e>] __btrfs_write_out_cache.isra.14+0x2d9/0x3a7 [btrfs] [17156.864052] [<ffffffffa03ac1ab>] ? btrfs_write_out_cache+0x41/0xdc [btrfs] [17156.864052] [<ffffffffa03ac1fd>] btrfs_write_out_cache+0x93/0xdc [btrfs] [17156.864052] [<ffffffffa0363847>] ? btrfs_start_dirty_block_groups+0x13a/0x2b2 [btrfs] [17156.864052] [<ffffffffa03638e6>] btrfs_start_dirty_block_groups+0x1d9/0x2b2 [btrfs] [17156.864052] [<ffffffff8107d33d>] ? trace_hardirqs_on+0xd/0xf [17156.864052] [<ffffffffa037209e>] btrfs_commit_transaction+0x130/0x9c9 [btrfs] [17156.864052] [<ffffffffa034c748>] btrfs_sync_fs+0xe1/0x12d [btrfs] Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Chris Mason <clm@fb.com>
2015-05-06 02:03:10 +08:00
return ret_wb ? ret_wb : ret;
}
/*
* find an ordered extent corresponding to file_offset. return NULL if
* nothing is found, otherwise take a reference on the extent and return it
*/
struct btrfs_ordered_extent *btrfs_lookup_ordered_extent(struct inode *inode,
u64 file_offset)
{
struct btrfs_ordered_inode_tree *tree;
struct rb_node *node;
struct btrfs_ordered_extent *entry = NULL;
tree = &BTRFS_I(inode)->ordered_tree;
spin_lock_irq(&tree->lock);
node = tree_search(tree, file_offset);
if (!node)
goto out;
entry = rb_entry(node, struct btrfs_ordered_extent, rb_node);
if (!offset_in_entry(entry, file_offset))
entry = NULL;
if (entry)
refcount_inc(&entry->refs);
out:
spin_unlock_irq(&tree->lock);
return entry;
}
/* Since the DIO code tries to lock a wide area we need to look for any ordered
* extents that exist in the range, rather than just the start of the range.
*/
struct btrfs_ordered_extent *btrfs_lookup_ordered_range(
struct btrfs_inode *inode, u64 file_offset, u64 len)
{
struct btrfs_ordered_inode_tree *tree;
struct rb_node *node;
struct btrfs_ordered_extent *entry = NULL;
tree = &inode->ordered_tree;
spin_lock_irq(&tree->lock);
node = tree_search(tree, file_offset);
if (!node) {
node = tree_search(tree, file_offset + len);
if (!node)
goto out;
}
while (1) {
entry = rb_entry(node, struct btrfs_ordered_extent, rb_node);
if (range_overlaps(entry, file_offset, len))
break;
if (entry->file_offset >= file_offset + len) {
entry = NULL;
break;
}
entry = NULL;
node = rb_next(node);
if (!node)
break;
}
out:
if (entry)
refcount_inc(&entry->refs);
spin_unlock_irq(&tree->lock);
return entry;
}
/*
* lookup and return any extent before 'file_offset'. NULL is returned
* if none is found
*/
struct btrfs_ordered_extent *
btrfs_lookup_first_ordered_extent(struct inode *inode, u64 file_offset)
{
struct btrfs_ordered_inode_tree *tree;
struct rb_node *node;
struct btrfs_ordered_extent *entry = NULL;
tree = &BTRFS_I(inode)->ordered_tree;
spin_lock_irq(&tree->lock);
node = tree_search(tree, file_offset);
if (!node)
goto out;
entry = rb_entry(node, struct btrfs_ordered_extent, rb_node);
refcount_inc(&entry->refs);
out:
spin_unlock_irq(&tree->lock);
return entry;
}
/*
* After an extent is done, call this to conditionally update the on disk
* i_size. i_size is updated to cover any fully written part of the file.
*/
int btrfs_ordered_update_i_size(struct inode *inode, u64 offset,
struct btrfs_ordered_extent *ordered)
{
struct btrfs_ordered_inode_tree *tree = &BTRFS_I(inode)->ordered_tree;
u64 disk_i_size;
u64 new_i_size;
u64 i_size = i_size_read(inode);
struct rb_node *node;
struct rb_node *prev = NULL;
struct btrfs_ordered_extent *test;
int ret = 1;
btrfs: fix disk_i_size update bug when fallocate() fails When doing truncate operation, btrfs_setsize() will first call truncate_setsize() to set new inode->i_size, but if later btrfs_truncate() fails, btrfs_setsize() will call "i_size_write(inode, BTRFS_I(inode)->disk_i_size)" to reset the inmemory inode size, now bug occurs. It's because for truncate case btrfs_ordered_update_i_size() directly uses inode->i_size to update BTRFS_I(inode)->disk_i_size, indeed we should use the "offset" argument to update disk_i_size. Here is the call graph: ==>btrfs_truncate() ====>btrfs_truncate_inode_items() ======>btrfs_ordered_update_i_size(inode, last_size, NULL); Here btrfs_ordered_update_i_size()'s offset argument is last_size. And below test case can reveal this bug: dd if=/dev/zero of=fs.img bs=$((1024*1024)) count=100 dev=$(losetup --show -f fs.img) mkdir -p /mnt/mntpoint mkfs.btrfs -f $dev mount $dev /mnt/mntpoint cd /mnt/mntpoint echo "workdir is: /mnt/mntpoint" blocksize=$((128 * 1024)) dd if=/dev/zero of=testfile bs=$blocksize count=1 sync count=$((17*1024*1024*1024/blocksize)) echo "file size is:" $((count*blocksize)) for ((i = 1; i <= $count; i++)); do i=$((i + 1)) dst_offset=$((blocksize * i)) xfs_io -f -c "reflink testfile 0 $dst_offset $blocksize"\ testfile > /dev/null done sync truncate --size 0 testfile ls -l testfile du -sh testfile exit In this case, truncate operation will fail for enospc reason and "du -sh testfile" returns value greater than 0, but testfile's size is 0, we need to reflect correct inode->i_size. Signed-off-by: Wang Xiaoguang <wangxg.fnst@cn.fujitsu.com> Signed-off-by: David Sterba <dsterba@suse.com> Signed-off-by: Chris Mason <clm@fb.com>
2016-06-22 09:57:01 +08:00
u64 orig_offset = offset;
spin_lock_irq(&tree->lock);
if (ordered) {
offset = entry_end(ordered);
if (test_bit(BTRFS_ORDERED_TRUNCATED, &ordered->flags))
offset = min(offset,
ordered->file_offset +
ordered->truncated_len);
} else {
offset = ALIGN(offset, btrfs_inode_sectorsize(inode));
}
disk_i_size = BTRFS_I(inode)->disk_i_size;
/*
* truncate file.
* If ordered is not NULL, then this is called from endio and
* disk_i_size will be updated by either truncate itself or any
* in-flight IOs which are inside the disk_i_size.
*
* Because btrfs_setsize() may set i_size with disk_i_size if truncate
* fails somehow, we need to make sure we have a precise disk_i_size by
* updating it as usual.
*
*/
if (!ordered && disk_i_size > i_size) {
btrfs: fix disk_i_size update bug when fallocate() fails When doing truncate operation, btrfs_setsize() will first call truncate_setsize() to set new inode->i_size, but if later btrfs_truncate() fails, btrfs_setsize() will call "i_size_write(inode, BTRFS_I(inode)->disk_i_size)" to reset the inmemory inode size, now bug occurs. It's because for truncate case btrfs_ordered_update_i_size() directly uses inode->i_size to update BTRFS_I(inode)->disk_i_size, indeed we should use the "offset" argument to update disk_i_size. Here is the call graph: ==>btrfs_truncate() ====>btrfs_truncate_inode_items() ======>btrfs_ordered_update_i_size(inode, last_size, NULL); Here btrfs_ordered_update_i_size()'s offset argument is last_size. And below test case can reveal this bug: dd if=/dev/zero of=fs.img bs=$((1024*1024)) count=100 dev=$(losetup --show -f fs.img) mkdir -p /mnt/mntpoint mkfs.btrfs -f $dev mount $dev /mnt/mntpoint cd /mnt/mntpoint echo "workdir is: /mnt/mntpoint" blocksize=$((128 * 1024)) dd if=/dev/zero of=testfile bs=$blocksize count=1 sync count=$((17*1024*1024*1024/blocksize)) echo "file size is:" $((count*blocksize)) for ((i = 1; i <= $count; i++)); do i=$((i + 1)) dst_offset=$((blocksize * i)) xfs_io -f -c "reflink testfile 0 $dst_offset $blocksize"\ testfile > /dev/null done sync truncate --size 0 testfile ls -l testfile du -sh testfile exit In this case, truncate operation will fail for enospc reason and "du -sh testfile" returns value greater than 0, but testfile's size is 0, we need to reflect correct inode->i_size. Signed-off-by: Wang Xiaoguang <wangxg.fnst@cn.fujitsu.com> Signed-off-by: David Sterba <dsterba@suse.com> Signed-off-by: Chris Mason <clm@fb.com>
2016-06-22 09:57:01 +08:00
BTRFS_I(inode)->disk_i_size = orig_offset;
ret = 0;
goto out;
}
/*
* if the disk i_size is already at the inode->i_size, or
* this ordered extent is inside the disk i_size, we're done
*/
if (disk_i_size == i_size)
goto out;
/*
* We still need to update disk_i_size if outstanding_isize is greater
* than disk_i_size.
*/
if (offset <= disk_i_size &&
(!ordered || ordered->outstanding_isize <= disk_i_size))
goto out;
/*
* walk backward from this ordered extent to disk_i_size.
* if we find an ordered extent then we can't update disk i_size
* yet
*/
if (ordered) {
node = rb_prev(&ordered->rb_node);
} else {
prev = tree_search(tree, offset);
/*
* we insert file extents without involving ordered struct,
* so there should be no ordered struct cover this offset
*/
if (prev) {
test = rb_entry(prev, struct btrfs_ordered_extent,
rb_node);
BUG_ON(offset_in_entry(test, offset));
}
node = prev;
}
for (; node; node = rb_prev(node)) {
test = rb_entry(node, struct btrfs_ordered_extent, rb_node);
/* We treat this entry as if it doesn't exist */
if (test_bit(BTRFS_ORDERED_UPDATED_ISIZE, &test->flags))
continue;
if (entry_end(test) <= disk_i_size)
break;
if (test->file_offset >= i_size)
break;
/*
* We don't update disk_i_size now, so record this undealt
* i_size. Or we will not know the real i_size.
*/
if (test->outstanding_isize < offset)
test->outstanding_isize = offset;
if (ordered &&
ordered->outstanding_isize > test->outstanding_isize)
test->outstanding_isize = ordered->outstanding_isize;
goto out;
}
new_i_size = min_t(u64, offset, i_size);
/*
* Some ordered extents may completed before the current one, and
* we hold the real i_size in ->outstanding_isize.
*/
if (ordered && ordered->outstanding_isize > new_i_size)
new_i_size = min_t(u64, ordered->outstanding_isize, i_size);
BTRFS_I(inode)->disk_i_size = new_i_size;
ret = 0;
out:
/*
* We need to do this because we can't remove ordered extents until
* after the i_disk_size has been updated and then the inode has been
* updated to reflect the change, so we need to tell anybody who finds
* this ordered extent that we've already done all the real work, we
* just haven't completed all the other work.
*/
if (ordered)
set_bit(BTRFS_ORDERED_UPDATED_ISIZE, &ordered->flags);
spin_unlock_irq(&tree->lock);
return ret;
}
/*
* search the ordered extents for one corresponding to 'offset' and
* try to find a checksum. This is used because we allow pages to
* be reclaimed before their checksum is actually put into the btree
*/
Btrfs: move data checksumming into a dedicated tree Btrfs stores checksums for each data block. Until now, they have been stored in the subvolume trees, indexed by the inode that is referencing the data block. This means that when we read the inode, we've probably read in at least some checksums as well. But, this has a few problems: * The checksums are indexed by logical offset in the file. When compression is on, this means we have to do the expensive checksumming on the uncompressed data. It would be faster if we could checksum the compressed data instead. * If we implement encryption, we'll be checksumming the plain text and storing that on disk. This is significantly less secure. * For either compression or encryption, we have to get the plain text back before we can verify the checksum as correct. This makes the raid layer balancing and extent moving much more expensive. * It makes the front end caching code more complex, as we have touch the subvolume and inodes as we cache extents. * There is potentitally one copy of the checksum in each subvolume referencing an extent. The solution used here is to store the extent checksums in a dedicated tree. This allows us to index the checksums by phyiscal extent start and length. It means: * The checksum is against the data stored on disk, after any compression or encryption is done. * The checksum is stored in a central location, and can be verified without following back references, or reading inodes. This makes compression significantly faster by reducing the amount of data that needs to be checksummed. It will also allow much faster raid management code in general. The checksums are indexed by a key with a fixed objectid (a magic value in ctree.h) and offset set to the starting byte of the extent. This allows us to copy the checksum items into the fsync log tree directly (or any other tree), without having to invent a second format for them. Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-12-09 05:58:54 +08:00
int btrfs_find_ordered_sum(struct inode *inode, u64 offset, u64 disk_bytenr,
u32 *sum, int len)
{
struct btrfs_ordered_sum *ordered_sum;
struct btrfs_ordered_extent *ordered;
struct btrfs_ordered_inode_tree *tree = &BTRFS_I(inode)->ordered_tree;
unsigned long num_sectors;
unsigned long i;
u32 sectorsize = btrfs_inode_sectorsize(inode);
int index = 0;
ordered = btrfs_lookup_ordered_extent(inode, offset);
if (!ordered)
return 0;
spin_lock_irq(&tree->lock);
list_for_each_entry_reverse(ordered_sum, &ordered->list, list) {
if (disk_bytenr >= ordered_sum->bytenr &&
disk_bytenr < ordered_sum->bytenr + ordered_sum->len) {
i = (disk_bytenr - ordered_sum->bytenr) >>
inode->i_sb->s_blocksize_bits;
num_sectors = ordered_sum->len >>
inode->i_sb->s_blocksize_bits;
num_sectors = min_t(int, len - index, num_sectors - i);
memcpy(sum + index, ordered_sum->sums + i,
num_sectors);
index += (int)num_sectors;
if (index == len)
goto out;
disk_bytenr += num_sectors * sectorsize;
}
}
out:
spin_unlock_irq(&tree->lock);
btrfs_put_ordered_extent(ordered);
return index;
}
int __init ordered_data_init(void)
{
btrfs_ordered_extent_cache = kmem_cache_create("btrfs_ordered_extent",
sizeof(struct btrfs_ordered_extent), 0,
SLAB_MEM_SPREAD,
NULL);
if (!btrfs_ordered_extent_cache)
return -ENOMEM;
return 0;
}
void __cold ordered_data_exit(void)
{
kmem_cache_destroy(btrfs_ordered_extent_cache);
}