linux/fs/xfs/xfs_trans_extfree.c

296 lines
7.6 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (c) 2000,2005 Silicon Graphics, Inc.
* All Rights Reserved.
*/
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_bit.h"
#include "xfs_mount.h"
#include "xfs_defer.h"
#include "xfs_trans.h"
#include "xfs_trans_priv.h"
#include "xfs_extfree_item.h"
#include "xfs_alloc.h"
#include "xfs_bmap.h"
#include "xfs_trace.h"
/*
* This routine is called to allocate an "extent free done"
* log item that will hold nextents worth of extents. The
* caller must use all nextents extents, because we are not
* flexible about this at all.
*/
struct xfs_efd_log_item *
xfs_trans_get_efd(struct xfs_trans *tp,
struct xfs_efi_log_item *efip,
uint nextents)
{
struct xfs_efd_log_item *efdp;
ASSERT(tp != NULL);
ASSERT(nextents > 0);
efdp = xfs_efd_init(tp->t_mountp, efip, nextents);
ASSERT(efdp != NULL);
/*
* Get a log_item_desc to point at the new item.
*/
xfs_trans_add_item(tp, &efdp->efd_item);
return efdp;
}
/*
* Free an extent and log it to the EFD. Note that the transaction is marked
* dirty regardless of whether the extent free succeeds or fails to support the
* EFI/EFD lifecycle rules.
*/
int
xfs_trans_free_extent(
struct xfs_trans *tp,
struct xfs_efd_log_item *efdp,
xfs_fsblock_t start_block,
xfs: add owner field to extent allocation and freeing For the rmap btree to work, we have to feed the extent owner information to the the allocation and freeing functions. This information is what will end up in the rmap btree that tracks allocated extents. While we technically don't need the owner information when freeing extents, passing it allows us to validate that the extent we are removing from the rmap btree actually belonged to the owner we expected it to belong to. We also define a special set of owner values for internal metadata that would otherwise have no owner. This allows us to tell the difference between metadata owned by different per-ag btrees, as well as static fs metadata (e.g. AG headers) and internal journal blocks. There are also a couple of special cases we need to take care of - during EFI recovery, we don't actually know who the original owner was, so we need to pass a wildcard to indicate that we aren't checking the owner for validity. We also need special handling in growfs, as we "free" the space in the last AG when extending it, but because it's new space it has no actual owner... While touching the xfs_bmap_add_free() function, re-order the parameters to put the struct xfs_mount first. Extend the owner field to include both the owner type and some sort of index within the owner. The index field will be used to support reverse mappings when reflink is enabled. When we're freeing extents from an EFI, we don't have the owner information available (rmap updates have their own redo items). xfs_free_extent therefore doesn't need to do an rmap update. Make sure that the log replay code signals this correctly. This is based upon a patch originally from Dave Chinner. It has been extended to add more owner information with the intent of helping recovery operations when things go wrong (e.g. offset of user data block in a file). [dchinner: de-shout the xfs_rmap_*_owner helpers] [darrick: minor style fixes suggested by Christoph Hellwig] Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2016-08-03 01:33:42 +00:00
xfs_extlen_t ext_len,
struct xfs_owner_info *oinfo,
bool skip_discard)
{
struct xfs_mount *mp = tp->t_mountp;
uint next_extent;
xfs_agnumber_t agno = XFS_FSB_TO_AGNO(mp, start_block);
xfs_agblock_t agbno = XFS_FSB_TO_AGBNO(mp, start_block);
struct xfs_extent *extp;
int error;
trace_xfs_bmap_free_deferred(tp->t_mountp, agno, 0, agbno, ext_len);
error = __xfs_free_extent(tp, start_block, ext_len,
oinfo, XFS_AG_RESV_NONE, skip_discard);
/*
* Mark the transaction dirty, even on error. This ensures the
* transaction is aborted, which:
*
* 1.) releases the EFI and frees the EFD
* 2.) shuts down the filesystem
*/
tp->t_flags |= XFS_TRANS_DIRTY;
set_bit(XFS_LI_DIRTY, &efdp->efd_item.li_flags);
next_extent = efdp->efd_next_extent;
ASSERT(next_extent < efdp->efd_format.efd_nextents);
extp = &(efdp->efd_format.efd_extents[next_extent]);
extp->ext_start = start_block;
extp->ext_len = ext_len;
efdp->efd_next_extent++;
return error;
}
/* Sort bmap items by AG. */
static int
xfs_extent_free_diff_items(
void *priv,
struct list_head *a,
struct list_head *b)
{
struct xfs_mount *mp = priv;
struct xfs_extent_free_item *ra;
struct xfs_extent_free_item *rb;
ra = container_of(a, struct xfs_extent_free_item, xefi_list);
rb = container_of(b, struct xfs_extent_free_item, xefi_list);
return XFS_FSB_TO_AGNO(mp, ra->xefi_startblock) -
XFS_FSB_TO_AGNO(mp, rb->xefi_startblock);
}
/* Get an EFI. */
STATIC void *
xfs_extent_free_create_intent(
struct xfs_trans *tp,
unsigned int count)
{
struct xfs_efi_log_item *efip;
ASSERT(tp != NULL);
ASSERT(count > 0);
efip = xfs_efi_init(tp->t_mountp, count);
ASSERT(efip != NULL);
/*
* Get a log_item_desc to point at the new item.
*/
xfs_trans_add_item(tp, &efip->efi_item);
return efip;
}
/* Log a free extent to the intent item. */
STATIC void
xfs_extent_free_log_item(
struct xfs_trans *tp,
void *intent,
struct list_head *item)
{
struct xfs_efi_log_item *efip = intent;
struct xfs_extent_free_item *free;
uint next_extent;
struct xfs_extent *extp;
free = container_of(item, struct xfs_extent_free_item, xefi_list);
tp->t_flags |= XFS_TRANS_DIRTY;
set_bit(XFS_LI_DIRTY, &efip->efi_item.li_flags);
/*
* atomic_inc_return gives us the value after the increment;
* we want to use it as an array index so we need to subtract 1 from
* it.
*/
next_extent = atomic_inc_return(&efip->efi_next_extent) - 1;
ASSERT(next_extent < efip->efi_format.efi_nextents);
extp = &efip->efi_format.efi_extents[next_extent];
extp->ext_start = free->xefi_startblock;
extp->ext_len = free->xefi_blockcount;
}
/* Get an EFD so we can process all the free extents. */
STATIC void *
xfs_extent_free_create_done(
struct xfs_trans *tp,
void *intent,
unsigned int count)
{
return xfs_trans_get_efd(tp, intent, count);
}
/* Process a free extent. */
STATIC int
xfs_extent_free_finish_item(
struct xfs_trans *tp,
struct list_head *item,
void *done_item,
void **state)
{
struct xfs_extent_free_item *free;
int error;
free = container_of(item, struct xfs_extent_free_item, xefi_list);
error = xfs_trans_free_extent(tp, done_item,
free->xefi_startblock,
xfs: add owner field to extent allocation and freeing For the rmap btree to work, we have to feed the extent owner information to the the allocation and freeing functions. This information is what will end up in the rmap btree that tracks allocated extents. While we technically don't need the owner information when freeing extents, passing it allows us to validate that the extent we are removing from the rmap btree actually belonged to the owner we expected it to belong to. We also define a special set of owner values for internal metadata that would otherwise have no owner. This allows us to tell the difference between metadata owned by different per-ag btrees, as well as static fs metadata (e.g. AG headers) and internal journal blocks. There are also a couple of special cases we need to take care of - during EFI recovery, we don't actually know who the original owner was, so we need to pass a wildcard to indicate that we aren't checking the owner for validity. We also need special handling in growfs, as we "free" the space in the last AG when extending it, but because it's new space it has no actual owner... While touching the xfs_bmap_add_free() function, re-order the parameters to put the struct xfs_mount first. Extend the owner field to include both the owner type and some sort of index within the owner. The index field will be used to support reverse mappings when reflink is enabled. When we're freeing extents from an EFI, we don't have the owner information available (rmap updates have their own redo items). xfs_free_extent therefore doesn't need to do an rmap update. Make sure that the log replay code signals this correctly. This is based upon a patch originally from Dave Chinner. It has been extended to add more owner information with the intent of helping recovery operations when things go wrong (e.g. offset of user data block in a file). [dchinner: de-shout the xfs_rmap_*_owner helpers] [darrick: minor style fixes suggested by Christoph Hellwig] Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2016-08-03 01:33:42 +00:00
free->xefi_blockcount,
&free->xefi_oinfo, free->xefi_skip_discard);
kmem_free(free);
return error;
}
/* Abort all pending EFIs. */
STATIC void
xfs_extent_free_abort_intent(
void *intent)
{
xfs_efi_release(intent);
}
/* Cancel a free extent. */
STATIC void
xfs_extent_free_cancel_item(
struct list_head *item)
{
struct xfs_extent_free_item *free;
free = container_of(item, struct xfs_extent_free_item, xefi_list);
kmem_free(free);
}
static const struct xfs_defer_op_type xfs_extent_free_defer_type = {
.type = XFS_DEFER_OPS_TYPE_FREE,
.max_items = XFS_EFI_MAX_FAST_EXTENTS,
.diff_items = xfs_extent_free_diff_items,
.create_intent = xfs_extent_free_create_intent,
.abort_intent = xfs_extent_free_abort_intent,
.log_item = xfs_extent_free_log_item,
.create_done = xfs_extent_free_create_done,
.finish_item = xfs_extent_free_finish_item,
.cancel_item = xfs_extent_free_cancel_item,
};
xfs: defer agfl block frees when dfops is available The AGFL fixup code executes before every block allocation/free and rectifies the AGFL based on the current, dynamic allocation requirements of the fs. The AGFL must hold a minimum number of blocks to satisfy a worst case split of the free space btrees caused by the impending allocation operation. The AGFL is also updated to maintain the implicit requirement for a minimum number of free slots to satisfy a worst case join of the free space btrees. Since the AGFL caches individual blocks, AGFL reduction typically involves multiple, single block frees. We've had reports of transaction overrun problems during certain workloads that boil down to AGFL reduction freeing multiple blocks and consuming more space in the log than was reserved for the transaction. Since the objective of freeing AGFL blocks is to ensure free AGFL free slots are available for the upcoming allocation, one way to address this problem is to release surplus blocks from the AGFL immediately but defer the free of those blocks (similar to how file-mapped blocks are unmapped from the file in one transaction and freed via a deferred operation) until the transaction is rolled. This turns AGFL reduction into an operation with predictable log reservation consumption. Add the capability to defer AGFL block frees when a deferred ops list is available to the AGFL fixup code. Add a dfops pointer to the transaction to carry dfops through various contexts to the allocator context. Deferring AGFL frees is conditional behavior based on whether the transaction pointer is populated. The long term objective is to reuse the transaction pointer to clean up all unrelated callchains that pass dfops on the stack along with a transaction and in doing so, consistently defer AGFL blocks from the allocator. A bit of customization is required to handle deferred completion processing because AGFL blocks are accounted against a per-ag reservation pool and AGFL blocks are not inserted into the extent busy list when freed (they are inserted when used and released back to the AGFL). Reuse the majority of the existing deferred extent free infrastructure and customize it appropriately to handle AGFL blocks. Note that this patch only adds infrastructure. It does not change behavior because no callers have been updated to pass ->t_agfl_dfops into the allocation code. Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2018-05-08 00:38:47 +00:00
/*
* AGFL blocks are accounted differently in the reserve pools and are not
* inserted into the busy extent list.
*/
STATIC int
xfs_agfl_free_finish_item(
struct xfs_trans *tp,
struct list_head *item,
void *done_item,
void **state)
{
struct xfs_mount *mp = tp->t_mountp;
struct xfs_efd_log_item *efdp = done_item;
struct xfs_extent_free_item *free;
struct xfs_extent *extp;
struct xfs_buf *agbp;
int error;
xfs_agnumber_t agno;
xfs_agblock_t agbno;
uint next_extent;
free = container_of(item, struct xfs_extent_free_item, xefi_list);
ASSERT(free->xefi_blockcount == 1);
agno = XFS_FSB_TO_AGNO(mp, free->xefi_startblock);
agbno = XFS_FSB_TO_AGBNO(mp, free->xefi_startblock);
trace_xfs_agfl_free_deferred(mp, agno, 0, agbno, free->xefi_blockcount);
error = xfs_alloc_read_agf(mp, tp, agno, 0, &agbp);
if (!error)
error = xfs_free_agfl_block(tp, agno, agbno, agbp,
&free->xefi_oinfo);
/*
* Mark the transaction dirty, even on error. This ensures the
* transaction is aborted, which:
*
* 1.) releases the EFI and frees the EFD
* 2.) shuts down the filesystem
*/
tp->t_flags |= XFS_TRANS_DIRTY;
set_bit(XFS_LI_DIRTY, &efdp->efd_item.li_flags);
xfs: defer agfl block frees when dfops is available The AGFL fixup code executes before every block allocation/free and rectifies the AGFL based on the current, dynamic allocation requirements of the fs. The AGFL must hold a minimum number of blocks to satisfy a worst case split of the free space btrees caused by the impending allocation operation. The AGFL is also updated to maintain the implicit requirement for a minimum number of free slots to satisfy a worst case join of the free space btrees. Since the AGFL caches individual blocks, AGFL reduction typically involves multiple, single block frees. We've had reports of transaction overrun problems during certain workloads that boil down to AGFL reduction freeing multiple blocks and consuming more space in the log than was reserved for the transaction. Since the objective of freeing AGFL blocks is to ensure free AGFL free slots are available for the upcoming allocation, one way to address this problem is to release surplus blocks from the AGFL immediately but defer the free of those blocks (similar to how file-mapped blocks are unmapped from the file in one transaction and freed via a deferred operation) until the transaction is rolled. This turns AGFL reduction into an operation with predictable log reservation consumption. Add the capability to defer AGFL block frees when a deferred ops list is available to the AGFL fixup code. Add a dfops pointer to the transaction to carry dfops through various contexts to the allocator context. Deferring AGFL frees is conditional behavior based on whether the transaction pointer is populated. The long term objective is to reuse the transaction pointer to clean up all unrelated callchains that pass dfops on the stack along with a transaction and in doing so, consistently defer AGFL blocks from the allocator. A bit of customization is required to handle deferred completion processing because AGFL blocks are accounted against a per-ag reservation pool and AGFL blocks are not inserted into the extent busy list when freed (they are inserted when used and released back to the AGFL). Reuse the majority of the existing deferred extent free infrastructure and customize it appropriately to handle AGFL blocks. Note that this patch only adds infrastructure. It does not change behavior because no callers have been updated to pass ->t_agfl_dfops into the allocation code. Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2018-05-08 00:38:47 +00:00
next_extent = efdp->efd_next_extent;
ASSERT(next_extent < efdp->efd_format.efd_nextents);
extp = &(efdp->efd_format.efd_extents[next_extent]);
extp->ext_start = free->xefi_startblock;
extp->ext_len = free->xefi_blockcount;
efdp->efd_next_extent++;
kmem_free(free);
return error;
}
/* sub-type with special handling for AGFL deferred frees */
static const struct xfs_defer_op_type xfs_agfl_free_defer_type = {
.type = XFS_DEFER_OPS_TYPE_AGFL_FREE,
.max_items = XFS_EFI_MAX_FAST_EXTENTS,
.diff_items = xfs_extent_free_diff_items,
.create_intent = xfs_extent_free_create_intent,
.abort_intent = xfs_extent_free_abort_intent,
.log_item = xfs_extent_free_log_item,
.create_done = xfs_extent_free_create_done,
.finish_item = xfs_agfl_free_finish_item,
.cancel_item = xfs_extent_free_cancel_item,
};
/* Register the deferred op type. */
void
xfs_extent_free_init_defer_op(void)
{
xfs_defer_init_op_type(&xfs_extent_free_defer_type);
xfs: defer agfl block frees when dfops is available The AGFL fixup code executes before every block allocation/free and rectifies the AGFL based on the current, dynamic allocation requirements of the fs. The AGFL must hold a minimum number of blocks to satisfy a worst case split of the free space btrees caused by the impending allocation operation. The AGFL is also updated to maintain the implicit requirement for a minimum number of free slots to satisfy a worst case join of the free space btrees. Since the AGFL caches individual blocks, AGFL reduction typically involves multiple, single block frees. We've had reports of transaction overrun problems during certain workloads that boil down to AGFL reduction freeing multiple blocks and consuming more space in the log than was reserved for the transaction. Since the objective of freeing AGFL blocks is to ensure free AGFL free slots are available for the upcoming allocation, one way to address this problem is to release surplus blocks from the AGFL immediately but defer the free of those blocks (similar to how file-mapped blocks are unmapped from the file in one transaction and freed via a deferred operation) until the transaction is rolled. This turns AGFL reduction into an operation with predictable log reservation consumption. Add the capability to defer AGFL block frees when a deferred ops list is available to the AGFL fixup code. Add a dfops pointer to the transaction to carry dfops through various contexts to the allocator context. Deferring AGFL frees is conditional behavior based on whether the transaction pointer is populated. The long term objective is to reuse the transaction pointer to clean up all unrelated callchains that pass dfops on the stack along with a transaction and in doing so, consistently defer AGFL blocks from the allocator. A bit of customization is required to handle deferred completion processing because AGFL blocks are accounted against a per-ag reservation pool and AGFL blocks are not inserted into the extent busy list when freed (they are inserted when used and released back to the AGFL). Reuse the majority of the existing deferred extent free infrastructure and customize it appropriately to handle AGFL blocks. Note that this patch only adds infrastructure. It does not change behavior because no callers have been updated to pass ->t_agfl_dfops into the allocation code. Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2018-05-08 00:38:47 +00:00
xfs_defer_init_op_type(&xfs_agfl_free_defer_type);
}