static void set_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags)
{
- u64 extra_flags = flags & BTRFS_BLOCK_GROUP_PROFILE_MASK;
-
- /* chunk -> extended profile */
- if (extra_flags == 0)
- extra_flags = BTRFS_AVAIL_ALLOC_BIT_SINGLE;
+ u64 extra_flags = chunk_to_extended(flags) &
+ BTRFS_EXTENDED_PROFILE_MASK;
if (flags & BTRFS_BLOCK_GROUP_DATA)
fs_info->avail_data_alloc_bits |= extra_flags;
}
/*
+ * returns target flags in extended format or 0 if restripe for this
+ * chunk_type is not in progress
+ */
+static u64 get_restripe_target(struct btrfs_fs_info *fs_info, u64 flags)
+{
+ struct btrfs_balance_control *bctl = fs_info->balance_ctl;
+ u64 target = 0;
+
+ BUG_ON(!mutex_is_locked(&fs_info->volume_mutex) &&
+ !spin_is_locked(&fs_info->balance_lock));
+
+ if (!bctl)
+ return 0;
+
+ if (flags & BTRFS_BLOCK_GROUP_DATA &&
+ bctl->data.flags & BTRFS_BALANCE_ARGS_CONVERT) {
+ target = BTRFS_BLOCK_GROUP_DATA | bctl->data.target;
+ } else if (flags & BTRFS_BLOCK_GROUP_SYSTEM &&
+ bctl->sys.flags & BTRFS_BALANCE_ARGS_CONVERT) {
+ target = BTRFS_BLOCK_GROUP_SYSTEM | bctl->sys.target;
+ } else if (flags & BTRFS_BLOCK_GROUP_METADATA &&
+ bctl->meta.flags & BTRFS_BALANCE_ARGS_CONVERT) {
+ target = BTRFS_BLOCK_GROUP_METADATA | bctl->meta.target;
+ }
+
+ return target;
+}
+
+/*
* @flags: available profiles in extended format (see ctree.h)
*
* Returns reduced profile in chunk format. If profile changing is in
*/
u64 num_devices = root->fs_info->fs_devices->rw_devices +
root->fs_info->fs_devices->missing_devices;
+ u64 target;
- /* pick restriper's target profile if it's available */
+ /*
+ * see if restripe for this chunk_type is in progress, if so
+ * try to reduce to the target profile
+ */
spin_lock(&root->fs_info->balance_lock);
- if (root->fs_info->balance_ctl) {
- struct btrfs_balance_control *bctl = root->fs_info->balance_ctl;
- u64 tgt = 0;
-
- if ((flags & BTRFS_BLOCK_GROUP_DATA) &&
- (bctl->data.flags & BTRFS_BALANCE_ARGS_CONVERT) &&
- (flags & bctl->data.target)) {
- tgt = BTRFS_BLOCK_GROUP_DATA | bctl->data.target;
- } else if ((flags & BTRFS_BLOCK_GROUP_SYSTEM) &&
- (bctl->sys.flags & BTRFS_BALANCE_ARGS_CONVERT) &&
- (flags & bctl->sys.target)) {
- tgt = BTRFS_BLOCK_GROUP_SYSTEM | bctl->sys.target;
- } else if ((flags & BTRFS_BLOCK_GROUP_METADATA) &&
- (bctl->meta.flags & BTRFS_BALANCE_ARGS_CONVERT) &&
- (flags & bctl->meta.target)) {
- tgt = BTRFS_BLOCK_GROUP_METADATA | bctl->meta.target;
- }
-
- if (tgt) {
+ target = get_restripe_target(root->fs_info, flags);
+ if (target) {
+ /* pick target profile only if it's already available */
+ if ((flags & target) & BTRFS_EXTENDED_PROFILE_MASK) {
spin_unlock(&root->fs_info->balance_lock);
- flags = tgt;
- goto out;
+ return extended_to_chunk(target);
}
}
spin_unlock(&root->fs_info->balance_lock);
flags &= ~BTRFS_BLOCK_GROUP_RAID0;
}
-out:
- /* extended -> chunk profile */
- flags &= ~BTRFS_AVAIL_ALLOC_BIT_SINGLE;
- return flags;
+ return extended_to_chunk(flags);
}
static u64 get_alloc_profile(struct btrfs_root *root, u64 flags)
}
data_sinfo->bytes_may_use += bytes;
trace_btrfs_space_reservation(root->fs_info, "space_info",
- (u64)data_sinfo, bytes, 1);
+ (u64)(unsigned long)data_sinfo,
+ bytes, 1);
spin_unlock(&data_sinfo->lock);
return 0;
spin_lock(&data_sinfo->lock);
data_sinfo->bytes_may_use -= bytes;
trace_btrfs_space_reservation(root->fs_info, "space_info",
- (u64)data_sinfo, bytes, 0);
+ (u64)(unsigned long)data_sinfo,
+ bytes, 0);
spin_unlock(&data_sinfo->lock);
}
int wait_for_alloc = 0;
int ret = 0;
- BUG_ON(!profile_is_valid(flags, 0));
-
space_info = __find_space_info(extent_root->fs_info, flags);
if (!space_info) {
ret = update_space_info(extent_root->fs_info, flags,
if (used + orig_bytes <= space_info->total_bytes) {
space_info->bytes_may_use += orig_bytes;
trace_btrfs_space_reservation(root->fs_info,
- "space_info",
- (u64)space_info,
- orig_bytes, 1);
+ "space_info",
+ (u64)(unsigned long)space_info,
+ orig_bytes, 1);
ret = 0;
} else {
/*
if (used + num_bytes < space_info->total_bytes + avail) {
space_info->bytes_may_use += orig_bytes;
trace_btrfs_space_reservation(root->fs_info,
- "space_info",
- (u64)space_info,
- orig_bytes, 1);
+ "space_info",
+ (u64)(unsigned long)space_info,
+ orig_bytes, 1);
ret = 0;
} else {
wait_ordered = true;
spin_lock(&space_info->lock);
space_info->bytes_may_use -= num_bytes;
trace_btrfs_space_reservation(fs_info, "space_info",
- (u64)space_info,
- num_bytes, 0);
+ (u64)(unsigned long)space_info,
+ num_bytes, 0);
space_info->reservation_progress++;
spin_unlock(&space_info->lock);
}
num_bytes += div64_u64(data_used + meta_used, 50);
if (num_bytes * 3 > meta_used)
- num_bytes = div64_u64(meta_used, 3);
+ num_bytes = div64_u64(meta_used, 3) * 2;
return ALIGN(num_bytes, fs_info->extent_root->leafsize << 10);
}
block_rsv->reserved += num_bytes;
sinfo->bytes_may_use += num_bytes;
trace_btrfs_space_reservation(fs_info, "space_info",
- (u64)sinfo, num_bytes, 1);
+ (u64)(unsigned long)sinfo, num_bytes, 1);
}
if (block_rsv->reserved >= block_rsv->size) {
num_bytes = block_rsv->reserved - block_rsv->size;
sinfo->bytes_may_use -= num_bytes;
trace_btrfs_space_reservation(fs_info, "space_info",
- (u64)sinfo, num_bytes, 0);
+ (u64)(unsigned long)sinfo, num_bytes, 0);
sinfo->reservation_progress++;
block_rsv->reserved = block_rsv->size;
block_rsv->full = 1;
if (!trans->bytes_reserved)
return;
- trace_btrfs_space_reservation(root->fs_info, "transaction", (u64)trans,
+ trace_btrfs_space_reservation(root->fs_info, "transaction",
+ (u64)(unsigned long)trans,
trans->bytes_reserved, 0);
btrfs_block_rsv_release(root, trans->block_rsv, trans->bytes_reserved);
trans->bytes_reserved = 0;
space_info->bytes_reserved += num_bytes;
if (reserve == RESERVE_ALLOC) {
trace_btrfs_space_reservation(cache->fs_info,
- "space_info",
- (u64)space_info,
- num_bytes, 0);
+ "space_info",
+ (u64)(unsigned long)space_info,
+ num_bytes, 0);
space_info->bytes_may_use -= num_bytes;
}
}
if (is_data) {
ret = btrfs_del_csums(trans, root, bytenr, num_bytes);
BUG_ON(ret);
- } else {
- invalidate_mapping_pages(info->btree_inode->i_mapping,
- bytenr >> PAGE_CACHE_SHIFT,
- (bytenr + num_bytes - 1) >> PAGE_CACHE_SHIFT);
}
ret = update_block_group(trans, root, bytenr, num_bytes, 0);
return 0;
}
-static int get_block_group_index(struct btrfs_block_group_cache *cache)
+static int __get_block_group_index(u64 flags)
{
int index;
- if (cache->flags & BTRFS_BLOCK_GROUP_RAID10)
+
+ if (flags & BTRFS_BLOCK_GROUP_RAID10)
index = 0;
- else if (cache->flags & BTRFS_BLOCK_GROUP_RAID1)
+ else if (flags & BTRFS_BLOCK_GROUP_RAID1)
index = 1;
- else if (cache->flags & BTRFS_BLOCK_GROUP_DUP)
+ else if (flags & BTRFS_BLOCK_GROUP_DUP)
index = 2;
- else if (cache->flags & BTRFS_BLOCK_GROUP_RAID0)
+ else if (flags & BTRFS_BLOCK_GROUP_RAID0)
index = 3;
else
index = 4;
+
return index;
}
+static int get_block_group_index(struct btrfs_block_group_cache *cache)
+{
+ return __get_block_group_index(cache->flags);
+}
+
enum btrfs_loop_type {
- LOOP_FIND_IDEAL = 0,
- LOOP_CACHING_NOWAIT = 1,
- LOOP_CACHING_WAIT = 2,
- LOOP_ALLOC_CHUNK = 3,
- LOOP_NO_EMPTY_SIZE = 4,
+ LOOP_CACHING_NOWAIT = 0,
+ LOOP_CACHING_WAIT = 1,
+ LOOP_ALLOC_CHUNK = 2,
+ LOOP_NO_EMPTY_SIZE = 3,
};
/*
static noinline int find_free_extent(struct btrfs_trans_handle *trans,
struct btrfs_root *orig_root,
u64 num_bytes, u64 empty_size,
- u64 search_start, u64 search_end,
u64 hint_byte, struct btrfs_key *ins,
u64 data)
{
struct btrfs_free_cluster *last_ptr = NULL;
struct btrfs_block_group_cache *block_group = NULL;
struct btrfs_block_group_cache *used_block_group;
+ u64 search_start = 0;
int empty_cluster = 2 * 1024 * 1024;
int allowed_chunk_alloc = 0;
int done_chunk_alloc = 0;
bool failed_alloc = false;
bool use_cluster = true;
bool have_caching_bg = false;
- u64 ideal_cache_percent = 0;
- u64 ideal_cache_offset = 0;
WARN_ON(num_bytes < root->sectorsize);
btrfs_set_key_type(ins, BTRFS_EXTENT_ITEM_KEY);
empty_cluster = 0;
if (search_start == hint_byte) {
-ideal_cache:
block_group = btrfs_lookup_block_group(root->fs_info,
search_start);
used_block_group = block_group;
* picked out then we don't care that the block group is cached.
*/
if (block_group && block_group_bits(block_group, data) &&
- (block_group->cached != BTRFS_CACHE_NO ||
- search_start == ideal_cache_offset)) {
+ block_group->cached != BTRFS_CACHE_NO) {
down_read(&space_info->groups_sem);
if (list_empty(&block_group->list) ||
block_group->ro) {
have_block_group:
cached = block_group_cache_done(block_group);
if (unlikely(!cached)) {
- u64 free_percent;
-
found_uncached_bg = true;
ret = cache_block_group(block_group, trans,
- orig_root, 1);
- if (block_group->cached == BTRFS_CACHE_FINISHED)
- goto alloc;
-
- free_percent = btrfs_block_group_used(&block_group->item);
- free_percent *= 100;
- free_percent = div64_u64(free_percent,
- block_group->key.offset);
- free_percent = 100 - free_percent;
- if (free_percent > ideal_cache_percent &&
- likely(!block_group->ro)) {
- ideal_cache_offset = block_group->key.objectid;
- ideal_cache_percent = free_percent;
- }
-
- /*
- * The caching workers are limited to 2 threads, so we
- * can queue as much work as we care to.
- */
- if (loop > LOOP_FIND_IDEAL) {
- ret = cache_block_group(block_group, trans,
- orig_root, 0);
- BUG_ON(ret);
- }
-
- /*
- * If loop is set for cached only, try the next block
- * group.
- */
- if (loop == LOOP_FIND_IDEAL)
- goto loop;
+ orig_root, 0);
+ BUG_ON(ret);
}
-alloc:
if (unlikely(block_group->ro))
goto loop;
}
checks:
search_start = stripe_align(root, offset);
- /* move on to the next group */
- if (search_start + num_bytes >= search_end) {
- btrfs_add_free_space(used_block_group, offset, num_bytes);
- goto loop;
- }
/* move on to the next group */
if (search_start + num_bytes >
if (!ins->objectid && ++index < BTRFS_NR_RAID_TYPES)
goto search;
- /* LOOP_FIND_IDEAL, only search caching/cached bg's, and don't wait for
- * for them to make caching progress. Also
- * determine the best possible bg to cache
+ /*
* LOOP_CACHING_NOWAIT, search partially cached block groups, kicking
* caching kthreads as we move along
* LOOP_CACHING_WAIT, search everything, and wait if our bg is caching
*/
if (!ins->objectid && loop < LOOP_NO_EMPTY_SIZE) {
index = 0;
- if (loop == LOOP_FIND_IDEAL && found_uncached_bg) {
- found_uncached_bg = false;
- loop++;
- if (!ideal_cache_percent)
- goto search;
-
- /*
- * 1 of the following 2 things have happened so far
- *
- * 1) We found an ideal block group for caching that
- * is mostly full and will cache quickly, so we might
- * as well wait for it.
- *
- * 2) We searched for cached only and we didn't find
- * anything, and we didn't start any caching kthreads
- * either, so chances are we will loop through and
- * start a couple caching kthreads, and then come back
- * around and just wait for them. This will be slower
- * because we will have 2 caching kthreads reading at
- * the same time when we could have just started one
- * and waited for it to get far enough to give us an
- * allocation, so go ahead and go to the wait caching
- * loop.
- */
- loop = LOOP_CACHING_WAIT;
- search_start = ideal_cache_offset;
- ideal_cache_percent = 0;
- goto ideal_cache;
- } else if (loop == LOOP_FIND_IDEAL) {
- /*
- * Didn't find a uncached bg, wait on anything we find
- * next.
- */
- loop = LOOP_CACHING_WAIT;
- goto search;
- }
-
loop++;
-
if (loop == LOOP_ALLOC_CHUNK) {
if (allowed_chunk_alloc) {
ret = do_chunk_alloc(trans, root, num_bytes +
struct btrfs_root *root,
u64 num_bytes, u64 min_alloc_size,
u64 empty_size, u64 hint_byte,
- u64 search_end, struct btrfs_key *ins,
- u64 data)
+ struct btrfs_key *ins, u64 data)
{
bool final_tried = false;
int ret;
- u64 search_start = 0;
data = btrfs_get_alloc_profile(root, data);
again:
WARN_ON(num_bytes < root->sectorsize);
ret = find_free_extent(trans, root, num_bytes, empty_size,
- search_start, search_end, hint_byte,
- ins, data);
+ hint_byte, ins, data);
if (ret == -ENOSPC) {
if (!final_tried) {
btrfs_set_buffer_lockdep_class(root->root_key.objectid, buf, level);
btrfs_tree_lock(buf);
clean_tree_block(trans, root, buf);
+ clear_bit(EXTENT_BUFFER_STALE, &buf->bflags);
btrfs_set_lock_blocking(buf);
btrfs_set_buffer_uptodate(buf);
return ERR_CAST(block_rsv);
ret = btrfs_reserve_extent(trans, root, blocksize, blocksize,
- empty_size, hint, (u64)-1, &ins, 0);
+ empty_size, hint, &ins, 0);
if (ret) {
unuse_block_rsv(root->fs_info, block_rsv, blocksize);
return ERR_PTR(ret);
static u64 update_block_group_flags(struct btrfs_root *root, u64 flags)
{
u64 num_devices;
- u64 stripped = BTRFS_BLOCK_GROUP_RAID0 |
- BTRFS_BLOCK_GROUP_RAID1 | BTRFS_BLOCK_GROUP_RAID10;
+ u64 stripped;
- if (root->fs_info->balance_ctl) {
- struct btrfs_balance_control *bctl = root->fs_info->balance_ctl;
- u64 tgt = 0;
-
- /* pick restriper's target profile and return */
- if (flags & BTRFS_BLOCK_GROUP_DATA &&
- bctl->data.flags & BTRFS_BALANCE_ARGS_CONVERT) {
- tgt = BTRFS_BLOCK_GROUP_DATA | bctl->data.target;
- } else if (flags & BTRFS_BLOCK_GROUP_SYSTEM &&
- bctl->sys.flags & BTRFS_BALANCE_ARGS_CONVERT) {
- tgt = BTRFS_BLOCK_GROUP_SYSTEM | bctl->sys.target;
- } else if (flags & BTRFS_BLOCK_GROUP_METADATA &&
- bctl->meta.flags & BTRFS_BALANCE_ARGS_CONVERT) {
- tgt = BTRFS_BLOCK_GROUP_METADATA | bctl->meta.target;
- }
-
- if (tgt) {
- /* extended -> chunk profile */
- tgt &= ~BTRFS_AVAIL_ALLOC_BIT_SINGLE;
- return tgt;
- }
- }
+ /*
+ * if restripe for this chunk_type is on pick target profile and
+ * return, otherwise do the usual balance
+ */
+ stripped = get_restripe_target(root->fs_info, flags);
+ if (stripped)
+ return extended_to_chunk(stripped);
/*
* we add in the count of missing devices because we want
num_devices = root->fs_info->fs_devices->rw_devices +
root->fs_info->fs_devices->missing_devices;
+ stripped = BTRFS_BLOCK_GROUP_RAID0 |
+ BTRFS_BLOCK_GROUP_RAID1 | BTRFS_BLOCK_GROUP_RAID10;
+
if (num_devices == 1) {
stripped |= BTRFS_BLOCK_GROUP_DUP;
stripped = flags & ~stripped;
if (flags & (BTRFS_BLOCK_GROUP_RAID1 |
BTRFS_BLOCK_GROUP_RAID10))
return stripped | BTRFS_BLOCK_GROUP_DUP;
- return flags;
} else {
/* they already had raid on here, just return */
if (flags & stripped)
if (flags & BTRFS_BLOCK_GROUP_DUP)
return stripped | BTRFS_BLOCK_GROUP_RAID1;
- /* turn single device chunks into raid0 */
- return stripped | BTRFS_BLOCK_GROUP_RAID0;
+ /* this is drive concat, leave it alone */
}
+
return flags;
}
u64 min_free;
u64 dev_min = 1;
u64 dev_nr = 0;
+ u64 target;
int index;
int full = 0;
int ret = 0;
/*
* ok we don't have enough space, but maybe we have free space on our
* devices to allocate new chunks for relocation, so loop through our
- * alloc devices and guess if we have enough space. However, if we
- * were marked as full, then we know there aren't enough chunks, and we
- * can just return.
+ * alloc devices and guess if we have enough space. if this block
+ * group is going to be restriped, run checks against the target
+ * profile instead of the current one.
*/
ret = -1;
- if (full)
- goto out;
/*
* index:
* 3: raid0
* 4: single
*/
- index = get_block_group_index(block_group);
+ target = get_restripe_target(root->fs_info, block_group->flags);
+ if (target) {
+ index = __get_block_group_index(extended_to_chunk(target));
+ } else {
+ /*
+ * this is just a balance, so if we were marked as full
+ * we know there is no space for a new chunk
+ */
+ if (full)
+ goto out;
+
+ index = get_block_group_index(block_group);
+ }
+
if (index == 0) {
dev_min = 4;
/* Divide by 2 */
static void clear_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags)
{
- u64 extra_flags = flags & BTRFS_BLOCK_GROUP_PROFILE_MASK;
-
- /* chunk -> extended profile */
- if (extra_flags == 0)
- extra_flags = BTRFS_AVAIL_ALLOC_BIT_SINGLE;
+ u64 extra_flags = chunk_to_extended(flags) &
+ BTRFS_EXTENDED_PROFILE_MASK;
if (flags & BTRFS_BLOCK_GROUP_DATA)
fs_info->avail_data_alloc_bits &= ~extra_flags;