linux/fs/btrfs/free-space-cache.h

153 lines
5.2 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright (C) 2009 Oracle. All rights reserved.
*/
#ifndef BTRFS_FREE_SPACE_CACHE_H
#define BTRFS_FREE_SPACE_CACHE_H
/*
* This is the trim state of an extent or bitmap.
*
* BTRFS_TRIM_STATE_TRIMMING is special and used to maintain the state of a
* bitmap as we may need several trims to fully trim a single bitmap entry.
* This is reset should any free space other than trimmed space be added to the
* bitmap.
*/
enum btrfs_trim_state {
BTRFS_TRIM_STATE_UNTRIMMED,
BTRFS_TRIM_STATE_TRIMMED,
BTRFS_TRIM_STATE_TRIMMING,
};
Btrfs: use hybrid extents+bitmap rb tree for free space Currently btrfs has a problem where it can use a ridiculous amount of RAM simply tracking free space. As free space gets fragmented, we end up with thousands of entries on an rb-tree per block group, which usually spans 1 gig of area. Since we currently don't ever flush free space cache back to disk this gets to be a bit unweildly on large fs's with lots of fragmentation. This patch solves this problem by using PAGE_SIZE bitmaps for parts of the free space cache. Initially we calculate a threshold of extent entries we can handle, which is however many extent entries we can cram into 16k of ram. The maximum amount of RAM that should ever be used to track 1 gigabyte of diskspace will be 32k of RAM, which scales much better than we did before. Once we pass the extent threshold, we start adding bitmaps and using those instead for tracking the free space. This patch also makes it so that any free space thats less than 4 * sectorsize we go ahead and put into a bitmap. This is nice since we try and allocate out of the front of a block group, so if the front of a block group is heavily fragmented and then has a huge chunk of free space at the end, we go ahead and add the fragmented areas to bitmaps and use a normal extent entry to track the big chunk at the back of the block group. I've also taken the opportunity to revamp how we search for free space. Previously we indexed free space via an offset indexed rb tree and a bytes indexed rb tree. I've dropped the bytes indexed rb tree and use only the offset indexed rb tree. This cuts the number of tree operations we were doing previously down by half, and gives us a little bit of a better allocation pattern since we will always start from a specific offset and search forward from there, instead of searching for the size we need and try and get it as close as possible to the offset we want. I've given this a healthy amount of testing pre-new format stuff, as well as post-new format stuff. I've booted up my fedora box which is installed on btrfs with this patch and ran with it for a few days without issues. I've not seen any performance regressions in any of my tests. Since the last patch Yan Zheng fixed a problem where we could have overlapping entries, so updating their offset inline would cause problems. Thanks, Signed-off-by: Josef Bacik <jbacik@redhat.com> Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-07-14 09:29:25 +08:00
struct btrfs_free_space {
struct rb_node offset_index;
u64 offset;
u64 bytes;
u64 max_extent_size;
Btrfs: use hybrid extents+bitmap rb tree for free space Currently btrfs has a problem where it can use a ridiculous amount of RAM simply tracking free space. As free space gets fragmented, we end up with thousands of entries on an rb-tree per block group, which usually spans 1 gig of area. Since we currently don't ever flush free space cache back to disk this gets to be a bit unweildly on large fs's with lots of fragmentation. This patch solves this problem by using PAGE_SIZE bitmaps for parts of the free space cache. Initially we calculate a threshold of extent entries we can handle, which is however many extent entries we can cram into 16k of ram. The maximum amount of RAM that should ever be used to track 1 gigabyte of diskspace will be 32k of RAM, which scales much better than we did before. Once we pass the extent threshold, we start adding bitmaps and using those instead for tracking the free space. This patch also makes it so that any free space thats less than 4 * sectorsize we go ahead and put into a bitmap. This is nice since we try and allocate out of the front of a block group, so if the front of a block group is heavily fragmented and then has a huge chunk of free space at the end, we go ahead and add the fragmented areas to bitmaps and use a normal extent entry to track the big chunk at the back of the block group. I've also taken the opportunity to revamp how we search for free space. Previously we indexed free space via an offset indexed rb tree and a bytes indexed rb tree. I've dropped the bytes indexed rb tree and use only the offset indexed rb tree. This cuts the number of tree operations we were doing previously down by half, and gives us a little bit of a better allocation pattern since we will always start from a specific offset and search forward from there, instead of searching for the size we need and try and get it as close as possible to the offset we want. I've given this a healthy amount of testing pre-new format stuff, as well as post-new format stuff. I've booted up my fedora box which is installed on btrfs with this patch and ran with it for a few days without issues. I've not seen any performance regressions in any of my tests. Since the last patch Yan Zheng fixed a problem where we could have overlapping entries, so updating their offset inline would cause problems. Thanks, Signed-off-by: Josef Bacik <jbacik@redhat.com> Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-07-14 09:29:25 +08:00
unsigned long *bitmap;
struct list_head list;
enum btrfs_trim_state trim_state;
s32 bitmap_extents;
Btrfs: use hybrid extents+bitmap rb tree for free space Currently btrfs has a problem where it can use a ridiculous amount of RAM simply tracking free space. As free space gets fragmented, we end up with thousands of entries on an rb-tree per block group, which usually spans 1 gig of area. Since we currently don't ever flush free space cache back to disk this gets to be a bit unweildly on large fs's with lots of fragmentation. This patch solves this problem by using PAGE_SIZE bitmaps for parts of the free space cache. Initially we calculate a threshold of extent entries we can handle, which is however many extent entries we can cram into 16k of ram. The maximum amount of RAM that should ever be used to track 1 gigabyte of diskspace will be 32k of RAM, which scales much better than we did before. Once we pass the extent threshold, we start adding bitmaps and using those instead for tracking the free space. This patch also makes it so that any free space thats less than 4 * sectorsize we go ahead and put into a bitmap. This is nice since we try and allocate out of the front of a block group, so if the front of a block group is heavily fragmented and then has a huge chunk of free space at the end, we go ahead and add the fragmented areas to bitmaps and use a normal extent entry to track the big chunk at the back of the block group. I've also taken the opportunity to revamp how we search for free space. Previously we indexed free space via an offset indexed rb tree and a bytes indexed rb tree. I've dropped the bytes indexed rb tree and use only the offset indexed rb tree. This cuts the number of tree operations we were doing previously down by half, and gives us a little bit of a better allocation pattern since we will always start from a specific offset and search forward from there, instead of searching for the size we need and try and get it as close as possible to the offset we want. I've given this a healthy amount of testing pre-new format stuff, as well as post-new format stuff. I've booted up my fedora box which is installed on btrfs with this patch and ran with it for a few days without issues. I've not seen any performance regressions in any of my tests. Since the last patch Yan Zheng fixed a problem where we could have overlapping entries, so updating their offset inline would cause problems. Thanks, Signed-off-by: Josef Bacik <jbacik@redhat.com> Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-07-14 09:29:25 +08:00
};
static inline bool btrfs_free_space_trimmed(struct btrfs_free_space *info)
{
return (info->trim_state == BTRFS_TRIM_STATE_TRIMMED);
}
static inline bool btrfs_free_space_trimming_bitmap(
struct btrfs_free_space *info)
{
return (info->trim_state == BTRFS_TRIM_STATE_TRIMMING);
}
struct btrfs_free_space_ctl {
spinlock_t tree_lock;
struct rb_root free_space_offset;
u64 free_space;
int extents_thresh;
int free_extents;
int total_bitmaps;
int unit;
u64 start;
s32 discardable_extents[BTRFS_STAT_NR_ENTRIES];
s64 discardable_bytes[BTRFS_STAT_NR_ENTRIES];
const struct btrfs_free_space_op *op;
void *private;
Btrfs: fix race between writing free space cache and trimming Trimming is completely transactionless, and the way it operates consists of hiding free space entries from a block group, perform the trim/discard and then make the free space entries visible again. Therefore while a free space entry is being trimmed, we can have free space cache writing running in parallel (as part of a transaction commit) which will miss the free space entry. This means that an unmount (or crash/reboot) after that transaction commit and mount again before another transaction starts/commits after the discard finishes, we will have some free space that won't be used again unless the free space cache is rebuilt. After the unmount, fsck (btrfsck, btrfs check) reports the issue like the following example: *** fsck.btrfs output *** checking extents checking free space cache There is no free space entry for 521764864-521781248 There is no free space entry for 521764864-1103101952 cache appears valid but isnt 29360128 Checking filesystem on /dev/sdc UUID: b4789e27-4774-4626-98e9-ae8dfbfb0fb5 found 1235681286 bytes used err is -22 (...) Another issue caused by this race is a crash while writing bitmap entries to the cache, because while the cache writeout task accesses the bitmaps, the trim task can be concurrently modifying the bitmap or worse might be freeing the bitmap. The later case results in the following crash: [55650.804460] general protection fault: 0000 [#1] SMP DEBUG_PAGEALLOC [55650.804835] Modules linked in: btrfs dm_flakey dm_mod crc32c_generic xor raid6_pq nfsd auth_rpcgss oid_registry nfs_acl nfs lockd fscache sunrpc loop parport_pc parport i2c_piix4 psmouse evdev pcspkr microcode processor i2ccore serio_raw thermal_sys button ext4 crc16 jbd2 mbcache sg sd_mod crc_t10dif sr_mod cdrom crct10dif_generic crct10dif_common ata_generic virtio_scsi floppy ata_piix libata virtio_pci virtio_ring virtio scsi_mod e1000 [last unloaded: btrfs] [55650.806169] CPU: 1 PID: 31002 Comm: btrfs-transacti Tainted: G W 3.17.0-rc5-btrfs-next-1+ #1 [55650.806493] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.7.5-0-ge51488c-20140602_164612-nilsson.home.kraxel.org 04/01/2014 [55650.806867] task: ffff8800b12f6410 ti: ffff880071538000 task.ti: ffff880071538000 [55650.807166] RIP: 0010:[<ffffffffa037cf45>] [<ffffffffa037cf45>] write_bitmap_entries+0x65/0xbb [btrfs] [55650.807514] RSP: 0018:ffff88007153bc30 EFLAGS: 00010246 [55650.807687] RAX: 000000005d1ec000 RBX: ffff8800a665df08 RCX: 0000000000000400 [55650.807885] RDX: ffff88005d1ec000 RSI: 6b6b6b6b6b6b6b6b RDI: ffff88005d1ec000 [55650.808017] RBP: ffff88007153bc58 R08: 00000000ddd51536 R09: 00000000000001e0 [55650.808017] R10: 0000000000000000 R11: 0000000000000037 R12: 6b6b6b6b6b6b6b6b [55650.808017] R13: ffff88007153bca8 R14: 6b6b6b6b6b6b6b6b R15: ffff88007153bc98 [55650.808017] FS: 0000000000000000(0000) GS:ffff88023ec80000(0000) knlGS:0000000000000000 [55650.808017] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b [55650.808017] CR2: 0000000002273b88 CR3: 00000000b18f6000 CR4: 00000000000006e0 [55650.808017] Stack: [55650.808017] ffff88020e834e00 ffff880172d68db0 0000000000000000 ffff88019257c800 [55650.808017] ffff8801d42ea720 ffff88007153bd10 ffffffffa037d2fa ffff880224e99180 [55650.808017] ffff8801469a6188 ffff880224e99140 ffff880172d68c50 00000003000000b7 [55650.808017] Call Trace: [55650.808017] [<ffffffffa037d2fa>] __btrfs_write_out_cache+0x1ea/0x37f [btrfs] [55650.808017] [<ffffffffa037d959>] btrfs_write_out_cache+0xa1/0xd8 [btrfs] [55650.808017] [<ffffffffa033936b>] btrfs_write_dirty_block_groups+0x4b5/0x505 [btrfs] [55650.808017] [<ffffffffa03aa98e>] commit_cowonly_roots+0x15e/0x1f7 [btrfs] [55650.808017] [<ffffffff813eb9c7>] ? _raw_spin_lock+0xe/0x10 [55650.808017] [<ffffffffa0346e46>] btrfs_commit_transaction+0x411/0x882 [btrfs] [55650.808017] [<ffffffffa03432a4>] transaction_kthread+0xf2/0x1a4 [btrfs] [55650.808017] [<ffffffffa03431b2>] ? btrfs_cleanup_transaction+0x3d8/0x3d8 [btrfs] [55650.808017] [<ffffffff8105966b>] kthread+0xb7/0xbf [55650.808017] [<ffffffff810595b4>] ? __kthread_parkme+0x67/0x67 [55650.808017] [<ffffffff813ebeac>] ret_from_fork+0x7c/0xb0 [55650.808017] [<ffffffff810595b4>] ? __kthread_parkme+0x67/0x67 [55650.808017] Code: 4c 89 ef 8d 70 ff e8 d4 fc ff ff 41 8b 45 34 41 39 45 30 7d 5c 31 f6 4c 89 ef e8 80 f6 ff ff 49 8b 7d 00 4c 89 f6 b9 00 04 00 00 <f3> a5 4c 89 ef 41 8b 45 30 8d 70 ff e8 a3 fc ff ff 41 8b 45 34 [55650.808017] RIP [<ffffffffa037cf45>] write_bitmap_entries+0x65/0xbb [btrfs] [55650.808017] RSP <ffff88007153bc30> [55650.815725] ---[ end trace 1c032e96b149ff86 ]--- Fix this by serializing both tasks in such a way that cache writeout doesn't wait for the trim/discard of free space entries to finish and doesn't miss any free space entry. Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Chris Mason <clm@fb.com>
2014-12-02 01:04:09 +08:00
struct mutex cache_writeout_mutex;
struct list_head trimming_ranges;
};
struct btrfs_free_space_op {
bool (*use_bitmap)(struct btrfs_free_space_ctl *ctl,
struct btrfs_free_space *info);
};
struct btrfs_io_ctl {
void *cur, *orig;
struct page *page;
struct page **pages;
struct btrfs_fs_info *fs_info;
struct inode *inode;
unsigned long size;
int index;
int num_pages;
int entries;
int bitmaps;
};
struct inode *lookup_free_space_inode(struct btrfs_block_group *block_group,
struct btrfs_path *path);
int create_free_space_inode(struct btrfs_trans_handle *trans,
struct btrfs_block_group *block_group,
struct btrfs_path *path);
int btrfs_remove_free_space_inode(struct btrfs_trans_handle *trans,
struct inode *inode,
struct btrfs_block_group *block_group);
int btrfs_check_trunc_cache_free_space(struct btrfs_fs_info *fs_info,
struct btrfs_block_rsv *rsv);
int btrfs_truncate_free_space_cache(struct btrfs_trans_handle *trans,
struct btrfs_block_group *block_group,
struct inode *inode);
int load_free_space_cache(struct btrfs_block_group *block_group);
int btrfs_wait_cache_io(struct btrfs_trans_handle *trans,
struct btrfs_block_group *block_group,
struct btrfs_path *path);
int btrfs_write_out_cache(struct btrfs_trans_handle *trans,
struct btrfs_block_group *block_group,
struct btrfs_path *path);
void btrfs_init_free_space_ctl(struct btrfs_block_group *block_group,
struct btrfs_free_space_ctl *ctl);
int __btrfs_add_free_space(struct btrfs_fs_info *fs_info,
struct btrfs_free_space_ctl *ctl,
u64 bytenr, u64 size,
enum btrfs_trim_state trim_state);
int btrfs_add_free_space(struct btrfs_block_group *block_group,
u64 bytenr, u64 size);
int btrfs_add_free_space_unused(struct btrfs_block_group *block_group,
u64 bytenr, u64 size);
btrfs: add the beginning of async discard, discard workqueue When discard is enabled, everytime a pinned extent is released back to the block_group's free space cache, a discard is issued for the extent. This is an overeager approach when it comes to discarding and helping the SSD maintain enough free space to prevent severe garbage collection situations. This adds the beginning of async discard. Instead of issuing a discard prior to returning it to the free space, it is just marked as untrimmed. The block_group is then added to a LRU which then feeds into a workqueue to issue discards at a much slower rate. Full discarding of unused block groups is still done and will be addressed in a future patch of the series. For now, we don't persist the discard state of extents and bitmaps. Therefore, our failure recovery mode will be to consider extents untrimmed. This lets us handle failure and unmounting as one in the same. On a number of Facebook webservers, I collected data every minute accounting the time we spent in btrfs_finish_extent_commit() (col. 1) and in btrfs_commit_transaction() (col. 2). btrfs_finish_extent_commit() is where we discard extents synchronously before returning them to the free space cache. discard=sync: p99 total per minute p99 total per minute Drive | extent_commit() (ms) | commit_trans() (ms) --------------------------------------------------------------- Drive A | 434 | 1170 Drive B | 880 | 2330 Drive C | 2943 | 3920 Drive D | 4763 | 5701 discard=async: p99 total per minute p99 total per minute Drive | extent_commit() (ms) | commit_trans() (ms) -------------------------------------------------------------- Drive A | 134 | 956 Drive B | 64 | 1972 Drive C | 59 | 1032 Drive D | 62 | 1200 While it's not great that the stats are cumulative over 1m, all of these servers are running the same workload and and the delta between the two are substantial. We are spending significantly less time in btrfs_finish_extent_commit() which is responsible for discarding. Reviewed-by: Josef Bacik <josef@toxicpanda.com> Signed-off-by: Dennis Zhou <dennis@kernel.org> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2019-12-14 08:22:14 +08:00
int btrfs_add_free_space_async_trimmed(struct btrfs_block_group *block_group,
u64 bytenr, u64 size);
int btrfs_remove_free_space(struct btrfs_block_group *block_group,
u64 bytenr, u64 size);
void __btrfs_remove_free_space_cache(struct btrfs_free_space_ctl *ctl);
void btrfs_remove_free_space_cache(struct btrfs_block_group *block_group);
btrfs: handle empty block_group removal for async discard block_group removal is a little tricky. It can race with the extent allocator, the cleaner thread, and balancing. The current path is for a block_group to be added to the unused_bgs list. Then, when the cleaner thread comes around, it starts a transaction and then proceeds with removing the block_group. Extents that are pinned are subsequently removed from the pinned trees and then eventually a discard is issued for the entire block_group. Async discard introduces another player into the game, the discard workqueue. While it has none of the racing issues, the new problem is ensuring we don't leave free space untrimmed prior to forgetting the block_group. This is handled by placing fully free block_groups on a separate discard queue. This is necessary to maintain discarding order as in the future we will slowly trim even fully free block_groups. The ordering helps us make progress on the same block_group rather than say the last fully freed block_group or needing to search through the fully freed block groups at the beginning of a list and insert after. The new order of events is a fully freed block group gets placed on the unused discard queue first. Once it's processed, it will be placed on the unusued_bgs list and then the original sequence of events will happen, just without the final whole block_group discard. The mount flags can change when processing unused_bgs, so when flipping from DISCARD to DISCARD_ASYNC, the unused_bgs must be punted to the discard_list to be trimmed. If we flip off DISCARD_ASYNC, we punt free block groups on the discard_list to the unused_bg queue which will do the final discard for us. Reviewed-by: Josef Bacik <josef@toxicpanda.com> Signed-off-by: Dennis Zhou <dennis@kernel.org> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2019-12-14 08:22:15 +08:00
bool btrfs_is_free_space_trimmed(struct btrfs_block_group *block_group);
u64 btrfs_find_space_for_alloc(struct btrfs_block_group *block_group,
u64 offset, u64 bytes, u64 empty_size,
u64 *max_extent_size);
void btrfs_dump_free_space(struct btrfs_block_group *block_group,
u64 bytes);
int btrfs_find_space_cluster(struct btrfs_block_group *block_group,
struct btrfs_free_cluster *cluster,
u64 offset, u64 bytes, u64 empty_size);
void btrfs_init_free_cluster(struct btrfs_free_cluster *cluster);
u64 btrfs_alloc_from_cluster(struct btrfs_block_group *block_group,
struct btrfs_free_cluster *cluster, u64 bytes,
u64 min_start, u64 *max_extent_size);
void btrfs_return_cluster_to_free_space(
struct btrfs_block_group *block_group,
struct btrfs_free_cluster *cluster);
int btrfs_trim_block_group(struct btrfs_block_group *block_group,
u64 *trimmed, u64 start, u64 end, u64 minlen);
int btrfs_trim_block_group_extents(struct btrfs_block_group *block_group,
u64 *trimmed, u64 start, u64 end, u64 minlen,
bool async);
int btrfs_trim_block_group_bitmaps(struct btrfs_block_group *block_group,
u64 *trimmed, u64 start, u64 end, u64 minlen,
u64 maxlen, bool async);
bool btrfs_free_space_cache_v1_active(struct btrfs_fs_info *fs_info);
int btrfs_set_free_space_cache_v1_active(struct btrfs_fs_info *fs_info, bool active);
/* Support functions for running our sanity tests */
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
int test_add_free_space_entry(struct btrfs_block_group *cache,
u64 offset, u64 bytes, bool bitmap);
int test_check_exists(struct btrfs_block_group *cache, u64 offset, u64 bytes);
#endif
#endif