2008-03-24 12:01:56 -07:00
|
|
|
/*
|
|
|
|
* Copyright (C) 2007 Oracle. All rights reserved.
|
|
|
|
*
|
|
|
|
* This program is free software; you can redistribute it and/or
|
|
|
|
* modify it under the terms of the GNU General Public
|
|
|
|
* License v2 as published by the Free Software Foundation.
|
|
|
|
*
|
|
|
|
* This program is distributed in the hope that it will be useful,
|
|
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|
|
|
* General Public License for more details.
|
|
|
|
*
|
|
|
|
* You should have received a copy of the GNU General Public
|
|
|
|
* License along with this program; if not, write to the
|
|
|
|
* Free Software Foundation, Inc., 59 Temple Place - Suite 330,
|
|
|
|
* Boston, MA 021110-1307, USA.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#ifndef __BTRFS_VOLUMES_
|
|
|
|
#define __BTRFS_VOLUMES_
|
2008-04-03 13:29:03 -07:00
|
|
|
|
2008-04-09 13:28:12 -07:00
|
|
|
#include <linux/bio.h>
|
2011-01-05 03:07:28 -07:00
|
|
|
#include <linux/sort.h>
|
2008-06-11 13:50:36 -07:00
|
|
|
#include "async-thread.h"
|
2008-04-09 13:28:12 -07:00
|
|
|
|
2011-01-05 03:07:28 -07:00
|
|
|
#define BTRFS_STRIPE_LEN (64 * 1024)
|
|
|
|
|
2008-04-10 13:19:33 -07:00
|
|
|
struct buffer_head;
|
2009-04-20 12:50:09 -07:00
|
|
|
struct btrfs_pending_bios {
|
|
|
|
struct bio *head;
|
|
|
|
struct bio *tail;
|
|
|
|
};
|
|
|
|
|
2008-03-24 12:01:56 -07:00
|
|
|
struct btrfs_device {
|
|
|
|
struct list_head dev_list;
|
2008-04-22 06:22:07 -07:00
|
|
|
struct list_head dev_alloc_list;
|
2008-11-17 19:11:30 -07:00
|
|
|
struct btrfs_fs_devices *fs_devices;
|
2008-03-24 12:01:56 -07:00
|
|
|
struct btrfs_root *dev_root;
|
2009-04-20 12:50:09 -07:00
|
|
|
|
|
|
|
/* regular prio bios */
|
|
|
|
struct btrfs_pending_bios pending_bios;
|
|
|
|
/* WRITE_SYNC bios */
|
|
|
|
struct btrfs_pending_bios pending_sync_bios;
|
|
|
|
|
2008-06-11 13:50:36 -07:00
|
|
|
int running_pending;
|
2008-05-13 10:46:40 -07:00
|
|
|
u64 generation;
|
2008-04-22 06:22:07 -07:00
|
|
|
|
2008-11-17 19:11:30 -07:00
|
|
|
int writeable;
|
2008-05-13 10:46:40 -07:00
|
|
|
int in_fs_metadata;
|
2010-12-13 12:56:23 -07:00
|
|
|
int missing;
|
2011-08-04 07:52:27 -07:00
|
|
|
int can_discard;
|
2008-04-22 06:22:07 -07:00
|
|
|
|
2008-04-03 13:29:03 -07:00
|
|
|
spinlock_t io_lock;
|
2008-03-24 12:01:56 -07:00
|
|
|
|
|
|
|
struct block_device *bdev;
|
|
|
|
|
2010-11-13 03:55:18 -07:00
|
|
|
/* the mode sent to blkdev_get */
|
2008-11-19 19:17:22 -07:00
|
|
|
fmode_t mode;
|
|
|
|
|
2008-03-24 12:02:07 -07:00
|
|
|
char *name;
|
|
|
|
|
2008-03-24 12:01:56 -07:00
|
|
|
/* the internal btrfs device id */
|
|
|
|
u64 devid;
|
|
|
|
|
|
|
|
/* size of the device */
|
|
|
|
u64 total_bytes;
|
|
|
|
|
2009-04-27 04:29:03 -07:00
|
|
|
/* size of the disk */
|
|
|
|
u64 disk_total_bytes;
|
|
|
|
|
2008-03-24 12:01:56 -07:00
|
|
|
/* bytes used */
|
|
|
|
u64 bytes_used;
|
|
|
|
|
|
|
|
/* optimal io alignment for this device */
|
|
|
|
u32 io_align;
|
|
|
|
|
|
|
|
/* optimal io width for this device */
|
|
|
|
u32 io_width;
|
|
|
|
|
|
|
|
/* minimal io size for this device */
|
|
|
|
u32 sector_size;
|
|
|
|
|
|
|
|
/* type and info about this device */
|
|
|
|
u64 type;
|
|
|
|
|
|
|
|
/* physical drive uuid (or lvm uuid) */
|
2008-04-15 12:41:47 -07:00
|
|
|
u8 uuid[BTRFS_UUID_SIZE];
|
2008-06-11 13:50:36 -07:00
|
|
|
|
2011-03-08 06:14:00 -07:00
|
|
|
/* per-device scrub information */
|
|
|
|
struct scrub_dev *scrub_device;
|
|
|
|
|
2008-06-11 13:50:36 -07:00
|
|
|
struct btrfs_work work;
|
2011-04-20 03:09:16 -07:00
|
|
|
struct rcu_head rcu;
|
|
|
|
struct work_struct rcu_work;
|
2011-05-23 05:30:00 -07:00
|
|
|
|
|
|
|
/* readahead state */
|
|
|
|
spinlock_t reada_lock;
|
|
|
|
atomic_t reada_in_flight;
|
|
|
|
u64 reada_next;
|
|
|
|
struct reada_zone *reada_curr_zone;
|
|
|
|
struct radix_tree_root reada_zones;
|
|
|
|
struct radix_tree_root reada_extents;
|
2008-03-24 12:01:56 -07:00
|
|
|
};
|
|
|
|
|
2008-03-24 12:02:07 -07:00
|
|
|
struct btrfs_fs_devices {
|
|
|
|
u8 fsid[BTRFS_FSID_SIZE]; /* FS specific uuid */
|
|
|
|
|
2009-04-02 13:46:06 -07:00
|
|
|
/* the device with this id has the most recent copy of the super */
|
2008-03-24 12:02:07 -07:00
|
|
|
u64 latest_devid;
|
|
|
|
u64 latest_trans;
|
|
|
|
u64 num_devices;
|
2008-05-13 13:03:06 -07:00
|
|
|
u64 open_devices;
|
2008-11-17 19:11:30 -07:00
|
|
|
u64 rw_devices;
|
2010-12-13 12:56:23 -07:00
|
|
|
u64 missing_devices;
|
2008-11-17 19:11:30 -07:00
|
|
|
u64 total_rw_bytes;
|
2011-08-04 07:52:27 -07:00
|
|
|
u64 num_can_discard;
|
2008-03-24 12:02:07 -07:00
|
|
|
struct block_device *latest_bdev;
|
2009-06-10 12:17:02 -07:00
|
|
|
|
|
|
|
/* all of the devices in the FS, protected by a mutex
|
|
|
|
* so we can safely walk it to write out the supers without
|
|
|
|
* worrying about add/remove by the multi-device code
|
|
|
|
*/
|
|
|
|
struct mutex device_list_mutex;
|
2008-03-24 12:02:07 -07:00
|
|
|
struct list_head devices;
|
2008-04-22 06:22:07 -07:00
|
|
|
|
|
|
|
/* devices not currently being allocated */
|
|
|
|
struct list_head alloc_list;
|
2008-03-24 12:02:07 -07:00
|
|
|
struct list_head list;
|
2008-11-17 19:11:30 -07:00
|
|
|
|
|
|
|
struct btrfs_fs_devices *seed;
|
|
|
|
int seeding;
|
|
|
|
|
|
|
|
int opened;
|
2009-06-10 06:51:32 -07:00
|
|
|
|
|
|
|
/* set when we find or add a device that doesn't have the
|
|
|
|
* nonrot flag set
|
|
|
|
*/
|
|
|
|
int rotating;
|
2008-03-24 12:02:07 -07:00
|
|
|
};
|
|
|
|
|
2008-04-09 13:28:12 -07:00
|
|
|
struct btrfs_bio_stripe {
|
|
|
|
struct btrfs_device *dev;
|
|
|
|
u64 physical;
|
2011-03-24 03:24:26 -07:00
|
|
|
u64 length; /* only used for discard mappings */
|
2008-04-09 13:28:12 -07:00
|
|
|
};
|
|
|
|
|
2011-08-04 08:15:33 -07:00
|
|
|
struct btrfs_bio;
|
|
|
|
typedef void (btrfs_bio_end_io_t) (struct btrfs_bio *bio, int err);
|
|
|
|
|
|
|
|
struct btrfs_bio {
|
2008-04-09 13:28:12 -07:00
|
|
|
atomic_t stripes_pending;
|
|
|
|
bio_end_io_t *end_io;
|
2008-08-05 07:13:57 -07:00
|
|
|
struct bio *orig_bio;
|
2008-04-09 13:28:12 -07:00
|
|
|
void *private;
|
2008-04-29 06:38:00 -07:00
|
|
|
atomic_t error;
|
|
|
|
int max_errors;
|
2008-04-09 13:28:12 -07:00
|
|
|
int num_stripes;
|
2011-08-04 08:15:33 -07:00
|
|
|
int mirror_num;
|
2008-04-09 13:28:12 -07:00
|
|
|
struct btrfs_bio_stripe stripes[];
|
|
|
|
};
|
|
|
|
|
2011-01-05 03:07:28 -07:00
|
|
|
struct btrfs_device_info {
|
|
|
|
struct btrfs_device *dev;
|
|
|
|
u64 dev_offset;
|
|
|
|
u64 max_avail;
|
btrfs: quasi-round-robin for chunk allocation
In a multi device setup, the chunk allocator currently always allocates
chunks on the devices in the same order. This leads to a very uneven
distribution, especially with RAID1 or RAID10 and an uneven number of
devices.
This patch always sorts the devices before allocating, and allocates the
stripes on the devices with the most available space, as long as there
is enough space available. In a low space situation, it first tries to
maximize striping.
The patch also simplifies the allocator and reduces the checks for
corner cases.
The simplification is done by several means. First, it defines the
properties of each RAID type upfront. These properties are used afterwards
instead of differentiating cases in several places.
Second, the old allocator defined a minimum stripe size for each block
group type, tried to find a large enough chunk, and if this fails just
allocates a smaller one. This is now done in one step. The largest possible
chunk (up to max_chunk_size) is searched and allocated.
Because we now have only one pass, the allocation of the map (struct
map_lookup) is moved down to the point where the number of stripes is
already known. This way we avoid reallocation of the map.
We still avoid allocating stripes that are not a multiple of STRIPE_SIZE.
2011-04-12 03:07:57 -07:00
|
|
|
u64 total_avail;
|
2011-01-05 03:07:28 -07:00
|
|
|
};
|
|
|
|
|
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 04:18:59 -07:00
|
|
|
struct map_lookup {
|
|
|
|
u64 type;
|
|
|
|
int io_align;
|
|
|
|
int io_width;
|
|
|
|
int stripe_len;
|
|
|
|
int sector_size;
|
|
|
|
int num_stripes;
|
|
|
|
int sub_stripes;
|
|
|
|
struct btrfs_bio_stripe stripes[];
|
|
|
|
};
|
|
|
|
|
2011-03-08 06:14:00 -07:00
|
|
|
#define map_lookup_size(n) (sizeof(struct map_lookup) + \
|
|
|
|
(sizeof(struct btrfs_bio_stripe) * (n)))
|
|
|
|
|
btrfs: fix wrong free space information of btrfs
When we store data by raid profile in btrfs with two or more different size
disks, df command shows there is some free space in the filesystem, but the
user can not write any data in fact, df command shows the wrong free space
information of btrfs.
# mkfs.btrfs -d raid1 /dev/sda9 /dev/sda10
# btrfs-show
Label: none uuid: a95cd49e-6e33-45b8-8741-a36153ce4b64
Total devices 2 FS bytes used 28.00KB
devid 1 size 5.01GB used 2.03GB path /dev/sda9
devid 2 size 10.00GB used 2.01GB path /dev/sda10
# btrfs device scan /dev/sda9 /dev/sda10
# mount /dev/sda9 /mnt
# dd if=/dev/zero of=tmpfile0 bs=4K count=9999999999
(fill the filesystem)
# sync
# df -TH
Filesystem Type Size Used Avail Use% Mounted on
/dev/sda9 btrfs 17G 8.6G 5.4G 62% /mnt
# btrfs-show
Label: none uuid: a95cd49e-6e33-45b8-8741-a36153ce4b64
Total devices 2 FS bytes used 3.99GB
devid 1 size 5.01GB used 5.01GB path /dev/sda9
devid 2 size 10.00GB used 4.99GB path /dev/sda10
It is because btrfs cannot allocate chunks when one of the pairing disks has
no space, the free space on the other disks can not be used for ever, and should
be subtracted from the total space, but btrfs doesn't subtract this space from
the total. It is strange to the user.
This patch fixes it by calcing the free space that can be used to allocate
chunks.
Implementation:
1. get all the devices free space, and align them by stripe length.
2. sort the devices by the free space.
3. check the free space of the devices,
3.1. if it is not zero, and then check the number of the devices that has
more free space than this device,
if the number of the devices is beyond the min stripe number, the free
space can be used, and add into total free space.
if the number of the devices is below the min stripe number, we can not
use the free space, the check ends.
3.2. if the free space is zero, check the next devices, goto 3.1
This implementation is just likely fake chunk allocation.
After appling this patch, df can show correct space information:
# df -TH
Filesystem Type Size Used Avail Use% Mounted on
/dev/sda9 btrfs 17G 8.6G 0 100% /mnt
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2011-01-05 03:07:31 -07:00
|
|
|
int btrfs_account_dev_extents_size(struct btrfs_device *device, u64 start,
|
|
|
|
u64 end, u64 *length);
|
|
|
|
|
2011-08-04 08:15:33 -07:00
|
|
|
#define btrfs_bio_size(n) (sizeof(struct btrfs_bio) + \
|
2008-04-09 13:28:12 -07:00
|
|
|
(sizeof(struct btrfs_bio_stripe) * (n)))
|
|
|
|
|
2008-03-24 12:01:56 -07:00
|
|
|
int btrfs_alloc_dev_extent(struct btrfs_trans_handle *trans,
|
|
|
|
struct btrfs_device *device,
|
2008-04-15 12:41:47 -07:00
|
|
|
u64 chunk_tree, u64 chunk_objectid,
|
2008-11-17 19:11:30 -07:00
|
|
|
u64 chunk_offset, u64 start, u64 num_bytes);
|
2008-04-09 13:28:12 -07:00
|
|
|
int btrfs_map_block(struct btrfs_mapping_tree *map_tree, int rw,
|
|
|
|
u64 logical, u64 *length,
|
2011-08-04 08:15:33 -07:00
|
|
|
struct btrfs_bio **bbio_ret, int mirror_num);
|
2008-12-08 14:46:26 -07:00
|
|
|
int btrfs_rmap_block(struct btrfs_mapping_tree *map_tree,
|
|
|
|
u64 chunk_start, u64 physical, u64 devid,
|
|
|
|
u64 **logical, int *naddrs, int *stripe_len);
|
2008-12-12 08:03:26 -07:00
|
|
|
int btrfs_read_sys_array(struct btrfs_root *root);
|
2008-03-24 12:01:56 -07:00
|
|
|
int btrfs_read_chunk_tree(struct btrfs_root *root);
|
|
|
|
int btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
|
2008-11-17 19:11:30 -07:00
|
|
|
struct btrfs_root *extent_root, u64 type);
|
2008-03-24 12:01:56 -07:00
|
|
|
void btrfs_mapping_init(struct btrfs_mapping_tree *tree);
|
|
|
|
void btrfs_mapping_tree_free(struct btrfs_mapping_tree *tree);
|
2008-04-09 13:28:12 -07:00
|
|
|
int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio,
|
2008-06-11 13:50:36 -07:00
|
|
|
int mirror_num, int async_submit);
|
2008-03-24 12:02:07 -07:00
|
|
|
int btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
|
2008-12-02 04:36:09 -07:00
|
|
|
fmode_t flags, void *holder);
|
|
|
|
int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
|
2008-03-24 12:02:07 -07:00
|
|
|
struct btrfs_fs_devices **fs_devices_ret);
|
|
|
|
int btrfs_close_devices(struct btrfs_fs_devices *fs_devices);
|
2008-05-13 10:46:40 -07:00
|
|
|
int btrfs_close_extra_devices(struct btrfs_fs_devices *fs_devices);
|
2008-03-24 12:02:07 -07:00
|
|
|
int btrfs_add_device(struct btrfs_trans_handle *trans,
|
|
|
|
struct btrfs_root *root,
|
|
|
|
struct btrfs_device *device);
|
2008-05-07 08:43:44 -07:00
|
|
|
int btrfs_rm_device(struct btrfs_root *root, char *device_path);
|
2008-03-24 12:02:07 -07:00
|
|
|
int btrfs_cleanup_fs_uuids(void);
|
2008-04-09 13:28:12 -07:00
|
|
|
int btrfs_num_copies(struct btrfs_mapping_tree *map_tree, u64 logical, u64 len);
|
2008-04-25 13:53:30 -07:00
|
|
|
int btrfs_grow_device(struct btrfs_trans_handle *trans,
|
|
|
|
struct btrfs_device *device, u64 new_size);
|
|
|
|
struct btrfs_device *btrfs_find_device(struct btrfs_root *root, u64 devid,
|
2008-11-17 19:11:30 -07:00
|
|
|
u8 *uuid, u8 *fsid);
|
2008-04-25 13:53:30 -07:00
|
|
|
int btrfs_shrink_device(struct btrfs_device *device, u64 new_size);
|
2008-04-28 12:29:42 -07:00
|
|
|
int btrfs_init_new_device(struct btrfs_root *root, char *path);
|
2008-04-28 12:29:52 -07:00
|
|
|
int btrfs_balance(struct btrfs_root *dev_root);
|
2008-11-17 19:11:30 -07:00
|
|
|
int btrfs_chunk_readonly(struct btrfs_root *root, u64 chunk_offset);
|
Btrfs: make balance code choose more wisely when relocating
Currently, we can panic the box if the first block group we go to move is of a
type where there is no space left to move those extents. For example, if we
fill the disk up with data, and then we try to balance and we have no room to
move the data nor room to allocate new chunks, we will panic. Change this by
checking to see if we have room to move this chunk around, and if not, return
-ENOSPC and move on to the next chunk. This will make sure we remove block
groups that are moveable, like if we have alot of empty metadata block groups,
and then that way we make room to be able to balance our data chunks as well.
Tested this with an fs that would panic on btrfs-vol -b normally, but no longer
panics with this patch.
V1->V2:
-actually search for a free extent on the device to make sure we can allocate a
chunk if need be.
-fix btrfs_shrink_device to make sure we actually try to relocate all the
chunks, and then if we can't return -ENOSPC so if we are doing a btrfs-vol -r
we don't remove the device with data still on it.
-check to make sure the block group we are going to relocate isn't the last one
in that particular space
-fix a bug in btrfs_shrink_device where we would change the device's size and
not fix it if we fail to do our relocate
Signed-off-by: Josef Bacik <jbacik@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-09-11 13:11:19 -07:00
|
|
|
int find_free_dev_extent(struct btrfs_trans_handle *trans,
|
|
|
|
struct btrfs_device *device, u64 num_bytes,
|
|
|
|
u64 *start, u64 *max_avail);
|
2008-03-24 12:01:56 -07:00
|
|
|
#endif
|