linux/fs/xfs/xfs_extent_busy.h

91 lines
2.4 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (c) 2000-2002,2005 Silicon Graphics, Inc.
* Copyright (c) 2010 David Chinner.
* Copyright (c) 2011 Christoph Hellwig.
* All Rights Reserved.
*/
#ifndef __XFS_EXTENT_BUSY_H__
#define __XFS_EXTENT_BUSY_H__
struct xfs_mount;
struct xfs_perag;
struct xfs_trans;
struct xfs_alloc_arg;
/*
* Busy block/extent entry. Indexed by a rbtree in perag to mark blocks that
* have been freed but whose transactions aren't committed to disk yet.
*/
struct xfs_extent_busy {
struct rb_node rb_node; /* ag by-bno indexed search tree */
struct list_head list; /* transaction busy extent list */
xfs_agnumber_t agno;
xfs_agblock_t bno;
xfs_extlen_t length;
unsigned int flags;
#define XFS_EXTENT_BUSY_DISCARDED 0x01 /* undergoing a discard op. */
#define XFS_EXTENT_BUSY_SKIP_DISCARD 0x02 /* do not discard */
};
/*
* List used to track groups of related busy extents all the way through
* to discard completion.
*/
struct xfs_busy_extents {
struct xfs_mount *mount;
struct list_head extent_list;
struct work_struct endio_work;
/*
* Owner is the object containing the struct xfs_busy_extents to free
* once the busy extents have been processed. If only the
* xfs_busy_extents object needs freeing, then point this at itself.
*/
void *owner;
};
void
xfs_extent_busy_insert(struct xfs_trans *tp, struct xfs_perag *pag,
xfs_agblock_t bno, xfs_extlen_t len, unsigned int flags);
xfs: reduce AGF hold times during fstrim operations fstrim will hold the AGF lock for as long as it takes to walk and discard all the free space in the AG that meets the userspace trim criteria. For AGs with lots of free space extents (e.g. millions) or the underlying device is really slow at processing discard requests (e.g. Ceph RBD), this means the AGF hold time is often measured in minutes to hours, not a few milliseconds as we normal see with non-discard based operations. This can result in the entire filesystem hanging whilst the long-running fstrim is in progress. We can have transactions get stuck waiting for the AGF lock (data or metadata extent allocation and freeing), and then more transactions get stuck waiting on the locks those transactions hold. We can get to the point where fstrim blocks an extent allocation or free operation long enough that it ends up pinning the tail of the log and the log then runs out of space. At this point, every modification in the filesystem gets blocked. This includes read operations, if atime updates need to be made. To fix this problem, we need to be able to discard free space extents safely without holding the AGF lock. Fortunately, we already do this with online discard via busy extents. We can mark free space extents as "busy being discarded" under the AGF lock and then unlock the AGF, knowing that nobody will be able to allocate that free space extent until we remove it from the busy tree. Modify xfs_trim_extents to use the same asynchronous discard mechanism backed by busy extents as is used with online discard. This results in the AGF only needing to be held for short periods of time and it is never held while we issue discards. Hence if discard submission gets throttled because it is slow and/or there are lots of them, we aren't preventing other operations from being performed on AGF while we wait for discards to complete... Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Darrick J. Wong <djwong@kernel.org>
2023-10-04 06:24:52 +08:00
void
xfs_extent_busy_insert_discard(struct xfs_perag *pag, xfs_agblock_t bno,
xfs_extlen_t len, struct list_head *busy_list);
void
xfs_extent_busy_clear(struct xfs_mount *mp, struct list_head *list,
bool do_discard);
int
xfs_extent_busy_search(struct xfs_mount *mp, struct xfs_perag *pag,
xfs_agblock_t bno, xfs_extlen_t len);
void
xfs_extent_busy_reuse(struct xfs_mount *mp, struct xfs_perag *pag,
xfs_agblock_t fbno, xfs_extlen_t flen, bool userdata);
bool
xfs_extent_busy_trim(struct xfs_alloc_arg *args, xfs_agblock_t *bno,
xfs_extlen_t *len, unsigned *busy_gen);
xfs: don't block in busy flushing when freeing extents If the current transaction holds a busy extent and we are trying to allocate a new extent to fix up the free list, we can deadlock if the AG is entirely empty except for the busy extent held by the transaction. This can occur at runtime processing an XEFI with multiple extents in this path: __schedule+0x22f at ffffffff81f75e8f schedule+0x46 at ffffffff81f76366 xfs_extent_busy_flush+0x69 at ffffffff81477d99 xfs_alloc_ag_vextent_size+0x16a at ffffffff8141711a xfs_alloc_ag_vextent+0x19b at ffffffff81417edb xfs_alloc_fix_freelist+0x22f at ffffffff8141896f xfs_free_extent_fix_freelist+0x6a at ffffffff8141939a __xfs_free_extent+0x99 at ffffffff81419499 xfs_trans_free_extent+0x3e at ffffffff814a6fee xfs_extent_free_finish_item+0x24 at ffffffff814a70d4 xfs_defer_finish_noroll+0x1f7 at ffffffff81441407 xfs_defer_finish+0x11 at ffffffff814417e1 xfs_itruncate_extents_flags+0x13d at ffffffff8148b7dd xfs_inactive_truncate+0xb9 at ffffffff8148bb89 xfs_inactive+0x227 at ffffffff8148c4f7 xfs_fs_destroy_inode+0xb8 at ffffffff81496898 destroy_inode+0x3b at ffffffff8127d2ab do_unlinkat+0x1d1 at ffffffff81270df1 do_syscall_64+0x40 at ffffffff81f6b5f0 entry_SYSCALL_64_after_hwframe+0x44 at ffffffff8200007c This can also happen in log recovery when processing an EFI with multiple extents through this path: context_switch() kernel/sched/core.c:3881 __schedule() kernel/sched/core.c:5111 schedule() kernel/sched/core.c:5186 xfs_extent_busy_flush() fs/xfs/xfs_extent_busy.c:598 xfs_alloc_ag_vextent_size() fs/xfs/libxfs/xfs_alloc.c:1641 xfs_alloc_ag_vextent() fs/xfs/libxfs/xfs_alloc.c:828 xfs_alloc_fix_freelist() fs/xfs/libxfs/xfs_alloc.c:2362 xfs_free_extent_fix_freelist() fs/xfs/libxfs/xfs_alloc.c:3029 __xfs_free_extent() fs/xfs/libxfs/xfs_alloc.c:3067 xfs_trans_free_extent() fs/xfs/xfs_extfree_item.c:370 xfs_efi_recover() fs/xfs/xfs_extfree_item.c:626 xlog_recover_process_efi() fs/xfs/xfs_log_recover.c:4605 xlog_recover_process_intents() fs/xfs/xfs_log_recover.c:4893 xlog_recover_finish() fs/xfs/xfs_log_recover.c:5824 xfs_log_mount_finish() fs/xfs/xfs_log.c:764 xfs_mountfs() fs/xfs/xfs_mount.c:978 xfs_fs_fill_super() fs/xfs/xfs_super.c:1908 mount_bdev() fs/super.c:1417 xfs_fs_mount() fs/xfs/xfs_super.c:1985 legacy_get_tree() fs/fs_context.c:647 vfs_get_tree() fs/super.c:1547 do_new_mount() fs/namespace.c:2843 do_mount() fs/namespace.c:3163 ksys_mount() fs/namespace.c:3372 __do_sys_mount() fs/namespace.c:3386 __se_sys_mount() fs/namespace.c:3383 __x64_sys_mount() fs/namespace.c:3383 do_syscall_64() arch/x86/entry/common.c:296 entry_SYSCALL_64() arch/x86/entry/entry_64.S:180 To avoid this deadlock, we should not block in xfs_extent_busy_flush() if we hold a busy extent in the current transaction. Now that the EFI processing code can handle requeuing a partially completed EFI, we can detect this situation in xfs_extent_busy_flush() and return -EAGAIN rather than going to sleep forever. The -EAGAIN get propagated back out to the xfs_trans_free_extent() context, where the EFD is populated and the transaction is rolled, thereby moving the busy extents into the CIL. At this point, we can retry the extent free operation again with a clean transaction. If we hit the same "all free extents are busy" situation when trying to fix up the free list, we can safely call xfs_extent_busy_flush() and wait for the busy extents to resolve and wake us. At this point, the allocation search can make progress again and we can fix up the free list. This deadlock was first reported by Chandan in mid-2021, but I couldn't make myself understood during review, and didn't have time to fix it myself. It was reported again in March 2023, and again I have found myself unable to explain the complexities of the solution needed during review. As such, I don't have hours more time to waste trying to get the fix written the way it needs to be written, so I'm just doing it myself. This patchset is largely based on Wengang Wang's last patch, but with all the unnecessary stuff removed, split up into multiple patches and cleaned up somewhat. Reported-by: Chandan Babu R <chandanrlinux@gmail.com> Reported-by: Wengang Wang <wen.gang.wang@oracle.com> Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Darrick J. Wong <djwong@kernel.org> Signed-off-by: Darrick J. Wong <djwong@kernel.org>
2023-06-29 02:04:33 +08:00
int
xfs_extent_busy_flush(struct xfs_trans *tp, struct xfs_perag *pag,
unsigned busy_gen, uint32_t alloc_flags);
void
xfs_extent_busy_wait_all(struct xfs_mount *mp);
int
xfs_extent_busy_ag_cmp(void *priv, const struct list_head *a,
const struct list_head *b);
static inline void xfs_extent_busy_sort(struct list_head *list)
{
list_sort(NULL, list, xfs_extent_busy_ag_cmp);
}
bool xfs_extent_busy_list_empty(struct xfs_perag *pag);
#endif /* __XFS_EXTENT_BUSY_H__ */