AuxXxilium/linux_dsm_epyc7002
1
0
Fork 0
mirror of https://github.com/AuxXxilium/linux_dsm_epyc7002.git synced 2024-11-30 13:26:41 +07:00
Code Issues Actions Packages Projects Releases Wiki Activity
7cbe17701a
linux_dsm_epyc7002/fs/xfs/xfs_alloc.h
Dave Chinner ed3b4d6cdc xfs: Improve scalability of busy extent tracking 
When we free a metadata extent, we record it in the per-AG busy
extent array so that it is not re-used before the freeing
transaction hits the disk. This array is fixed size, so when it
overflows we make further allocation transactions synchronous
because we cannot track more freed extents until those transactions
hit the disk and are completed. Under heavy mixed allocation and
freeing workloads with large log buffers, we can overflow this array
quite easily.

Further, the array is sparsely populated, which means that inserts
need to search for a free slot, and array searches often have to
search many more slots that are actually used to check all the
busy extents. Quite inefficient, really.

To enable this aspect of extent freeing to scale better, we need
a structure that can grow dynamically. While in other areas of
XFS we have used radix trees, the extents being freed are at random
locations on disk so are better suited to being indexed by an rbtree.

So, use a per-AG rbtree indexed by block number to track busy
extents.  This incures a memory allocation when marking an extent
busy, but should not occur too often in low memory situations. This
should scale to an arbitrary number of extents so should not be a
limitation for features such as in-memory aggregation of
transactions.

However, there are still situations where we can't avoid allocating
busy extents (such as allocation from the AGFL). To minimise the
overhead of such occurences, we need to avoid doing a synchronous
log force while holding the AGF locked to ensure that the previous
transactions are safely on disk before we use the extent. We can do
this by marking the transaction doing the allocation as synchronous
rather issuing a log force.

Because of the locking involved and the ordering of transactions,
the synchronous transaction provides the same guarantees as a
synchronous log force because it ensures that all the prior
transactions are already on disk when the synchronous transaction
hits the disk. i.e. it preserves the free->allocate order of the
extent correctly in recovery.

By doing this, we avoid holding the AGF locked while log writes are
in progress, hence reducing the length of time the lock is held and
therefore we increase the rate at which we can allocate and free
from the allocation group, thereby increasing overall throughput.

The only problem with this approach is that when a metadata buffer is
marked stale (e.g. a directory block is removed), then buffer remains
pinned and locked until the log goes to disk. The issue here is that
if that stale buffer is reallocated in a subsequent transaction, the
attempt to lock that buffer in the transaction will hang waiting
the log to go to disk to unlock and unpin the buffer. Hence if
someone tries to lock a pinned, stale, locked buffer we need to
push on the log to get it unlocked ASAP. Effectively we are trading
off a guaranteed log force for a much less common trigger for log
force to occur.

Ideally we should not reallocate busy extents. That is a much more
complex fix to the problem as it involves direct intervention in the
allocation btree searches in many places. This is left to a future
set of modifications.

Finally, now that we track busy extents in allocated memory, we
don't need the descriptors in the transaction structure to point to
them. We can replace the complex busy chunk infrastructure with a
simple linked list of busy extents. This allows us to remove a large
chunk of code, making the overall change a net reduction in code
size.

Signed-off-by: Dave Chinner <david@fromorbit.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Alex Elder <aelder@sgi.com>
2010-05-24 10:34:00 -05:00

209 lines
7.1 KiB
C
Raw Blame History

/*
* Copyright (c) 2000-2002,2005 Silicon Graphics, Inc.
* 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 as
* published by the Free Software Foundation.
*
* This program is distributed in the hope that it would 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 the Free Software Foundation,
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
*/
#ifndef __XFS_ALLOC_H__
#define __XFS_ALLOC_H__
struct xfs_buf;
struct xfs_mount;
struct xfs_perag;
struct xfs_trans;
struct xfs_busy_extent;
/*
* Freespace allocation types. Argument to xfs_alloc_[v]extent.
*/
typedef enum xfs_alloctype
{
XFS_ALLOCTYPE_ANY_AG, /* allocate anywhere, use rotor */
XFS_ALLOCTYPE_FIRST_AG, /* ... start at ag 0 */
XFS_ALLOCTYPE_START_AG, /* anywhere, start in this a.g. */
XFS_ALLOCTYPE_THIS_AG, /* anywhere in this a.g. */
XFS_ALLOCTYPE_START_BNO, /* near this block else anywhere */
XFS_ALLOCTYPE_NEAR_BNO, /* in this a.g. and near this block */
XFS_ALLOCTYPE_THIS_BNO /* at exactly this block */
} xfs_alloctype_t;
#define XFS_ALLOC_TYPES \
{ XFS_ALLOCTYPE_ANY_AG, "ANY_AG" }, \
{ XFS_ALLOCTYPE_FIRST_AG, "FIRST_AG" }, \
{ XFS_ALLOCTYPE_START_AG, "START_AG" }, \
{ XFS_ALLOCTYPE_THIS_AG, "THIS_AG" }, \
{ XFS_ALLOCTYPE_START_BNO, "START_BNO" }, \
{ XFS_ALLOCTYPE_NEAR_BNO, "NEAR_BNO" }, \
{ XFS_ALLOCTYPE_THIS_BNO, "THIS_BNO" }
/*
* Flags for xfs_alloc_fix_freelist.
*/
#define XFS_ALLOC_FLAG_TRYLOCK 0x00000001 /* use trylock for buffer locking */
#define XFS_ALLOC_FLAG_FREEING 0x00000002 /* indicate caller is freeing extents*/
/*
* In order to avoid ENOSPC-related deadlock caused by
* out-of-order locking of AGF buffer (PV 947395), we place
* constraints on the relationship among actual allocations for
* data blocks, freelist blocks, and potential file data bmap
* btree blocks. However, these restrictions may result in no
* actual space allocated for a delayed extent, for example, a data
* block in a certain AG is allocated but there is no additional
* block for the additional bmap btree block due to a split of the
* bmap btree of the file. The result of this may lead to an
* infinite loop in xfssyncd when the file gets flushed to disk and
* all delayed extents need to be actually allocated. To get around
* this, we explicitly set aside a few blocks which will not be
* reserved in delayed allocation. Considering the minimum number of
* needed freelist blocks is 4 fsbs _per AG_, a potential split of file's bmap
* btree requires 1 fsb, so we set the number of set-aside blocks
* to 4 + 4*agcount.
*/
#define XFS_ALLOC_SET_ASIDE(mp) (4 + ((mp)->m_sb.sb_agcount * 4))
/*
* Argument structure for xfs_alloc routines.
* This is turned into a structure to avoid having 20 arguments passed
* down several levels of the stack.
*/
typedef struct xfs_alloc_arg {
struct xfs_trans *tp; /* transaction pointer */
struct xfs_mount *mp; /* file system mount point */
struct xfs_buf *agbp; /* buffer for a.g. freelist header */
struct xfs_perag *pag; /* per-ag struct for this agno */
xfs_fsblock_t fsbno; /* file system block number */
xfs_agnumber_t agno; /* allocation group number */
xfs_agblock_t agbno; /* allocation group-relative block # */
xfs_extlen_t minlen; /* minimum size of extent */
xfs_extlen_t maxlen; /* maximum size of extent */
xfs_extlen_t mod; /* mod value for extent size */
xfs_extlen_t prod; /* prod value for extent size */
xfs_extlen_t minleft; /* min blocks must be left after us */
xfs_extlen_t total; /* total blocks needed in xaction */
xfs_extlen_t alignment; /* align answer to multiple of this */
xfs_extlen_t minalignslop; /* slop for minlen+alignment calcs */
xfs_extlen_t len; /* output: actual size of extent */
xfs_alloctype_t type; /* allocation type XFS_ALLOCTYPE_... */
xfs_alloctype_t otype; /* original allocation type */
char wasdel; /* set if allocation was prev delayed */
char wasfromfl; /* set if allocation is from freelist */
char isfl; /* set if is freelist blocks - !acctg */
char userdata; /* set if this is user data */
xfs_fsblock_t firstblock; /* io first block allocated */
} xfs_alloc_arg_t;
/*
* Defines for userdata
*/
#define XFS_ALLOC_USERDATA 1 /* allocation is for user data*/
#define XFS_ALLOC_INITIAL_USER_DATA 2 /* special case start of file */
/*
* Find the length of the longest extent in an AG.
*/
xfs_extlen_t
xfs_alloc_longest_free_extent(struct xfs_mount *mp,
struct xfs_perag *pag);
#ifdef __KERNEL__
void
xfs_alloc_busy_insert(xfs_trans_t *tp,
xfs_agnumber_t agno,
xfs_agblock_t bno,
xfs_extlen_t len);
void
xfs_alloc_busy_clear(struct xfs_mount *mp, struct xfs_busy_extent *busyp);
#endif /* __KERNEL__ */
/*
* Compute and fill in value of m_ag_maxlevels.
*/
void
xfs_alloc_compute_maxlevels(
struct xfs_mount *mp); /* file system mount structure */
/*
* Get a block from the freelist.
* Returns with the buffer for the block gotten.
*/
int /* error */
xfs_alloc_get_freelist(
struct xfs_trans *tp, /* transaction pointer */
struct xfs_buf *agbp, /* buffer containing the agf structure */
xfs_agblock_t *bnop, /* block address retrieved from freelist */
int btreeblk); /* destination is a AGF btree */
/*
* Log the given fields from the agf structure.
*/
void
xfs_alloc_log_agf(
struct xfs_trans *tp, /* transaction pointer */
struct xfs_buf *bp, /* buffer for a.g. freelist header */
int fields);/* mask of fields to be logged (XFS_AGF_...) */
/*
* Interface for inode allocation to force the pag data to be initialized.
*/
int /* error */
xfs_alloc_pagf_init(
struct xfs_mount *mp, /* file system mount structure */
struct xfs_trans *tp, /* transaction pointer */
xfs_agnumber_t agno, /* allocation group number */
int flags); /* XFS_ALLOC_FLAGS_... */
/*
* Put the block on the freelist for the allocation group.
*/
int /* error */
xfs_alloc_put_freelist(
struct xfs_trans *tp, /* transaction pointer */
struct xfs_buf *agbp, /* buffer for a.g. freelist header */
struct xfs_buf *agflbp,/* buffer for a.g. free block array */
xfs_agblock_t bno, /* block being freed */
int btreeblk); /* owner was a AGF btree */
/*
* Read in the allocation group header (free/alloc section).
*/
int /* error */
xfs_alloc_read_agf(
struct xfs_mount *mp, /* mount point structure */
struct xfs_trans *tp, /* transaction pointer */
xfs_agnumber_t agno, /* allocation group number */
int flags, /* XFS_ALLOC_FLAG_... */
struct xfs_buf **bpp); /* buffer for the ag freelist header */
/*
* Allocate an extent (variable-size).
*/
int /* error */
xfs_alloc_vextent(
xfs_alloc_arg_t *args); /* allocation argument structure */
/*
* Free an extent.
*/
int /* error */
xfs_free_extent(
struct xfs_trans *tp, /* transaction pointer */
xfs_fsblock_t bno, /* starting block number of extent */
xfs_extlen_t len); /* length of extent */
#endif /* __XFS_ALLOC_H__ */
Reference in New Issue View Git Blame Copy Permalink