mirror of
https://github.com/adulau/aha.git
synced 2024-12-30 12:46:17 +00:00
92821e2ba4
When we have a couple of hundred transactions on the fly at once, they all typically modify the on disk superblock in some way. create/unclink/mkdir/rmdir modify inode counts, allocation/freeing modify free block counts. When these counts are modified in a transaction, they must eventually lock the superblock buffer and apply the mods. The buffer then remains locked until the transaction is committed into the incore log buffer. The result of this is that with enough transactions on the fly the incore superblock buffer becomes a bottleneck. The result of contention on the incore superblock buffer is that transaction rates fall - the more pressure that is put on the superblock buffer, the slower things go. The key to removing the contention is to not require the superblock fields in question to be locked. We do that by not marking the superblock dirty in the transaction. IOWs, we modify the incore superblock but do not modify the cached superblock buffer. In short, we do not log superblock modifications to critical fields in the superblock on every transaction. In fact we only do it just before we write the superblock to disk every sync period or just before unmount. This creates an interesting problem - if we don't log or write out the fields in every transaction, then how do the values get recovered after a crash? the answer is simple - we keep enough duplicate, logged information in other structures that we can reconstruct the correct count after log recovery has been performed. It is the AGF and AGI structures that contain the duplicate information; after recovery, we walk every AGI and AGF and sum their individual counters to get the correct value, and we do a transaction into the log to correct them. An optimisation of this is that if we have a clean unmount record, we know the value in the superblock is correct, so we can avoid the summation walk under normal conditions and so mount/recovery times do not change under normal operation. One wrinkle that was discovered during development was that the blocks used in the freespace btrees are never accounted for in the AGF counters. This was once a valid optimisation to make; when the filesystem is full, the free space btrees are empty and consume no space. Hence when it matters, the "accounting" is correct. But that means the when we do the AGF summations, we would not have a correct count and xfs_check would complain. Hence a new counter was added to track the number of blocks used by the free space btrees. This is an *on-disk format change*. As a result of this, lazy superblock counters are a mkfs option and at the moment on linux there is no way to convert an old filesystem. This is possible - xfs_db can be used to twiddle the right bits and then xfs_repair will do the format conversion for you. Similarly, you can convert backwards as well. At some point we'll add functionality to xfs_admin to do the bit twiddling easily.... SGI-PV: 964999 SGI-Modid: xfs-linux-melb:xfs-kern:28652a Signed-off-by: David Chinner <dgc@sgi.com> Signed-off-by: Christoph Hellwig <hch@infradead.org> Signed-off-by: Tim Shimmin <tes@sgi.com>
213 lines
7 KiB
C
213 lines
7 KiB
C
/*
|
|
* 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;
|
|
|
|
/*
|
|
* 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;
|
|
|
|
/*
|
|
* 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 */
|
|
|
|
|
|
#ifdef __KERNEL__
|
|
|
|
#if defined(XFS_ALLOC_TRACE)
|
|
/*
|
|
* Allocation tracing buffer size.
|
|
*/
|
|
#define XFS_ALLOC_TRACE_SIZE 4096
|
|
extern ktrace_t *xfs_alloc_trace_buf;
|
|
|
|
/*
|
|
* Types for alloc tracing.
|
|
*/
|
|
#define XFS_ALLOC_KTRACE_ALLOC 1
|
|
#define XFS_ALLOC_KTRACE_FREE 2
|
|
#define XFS_ALLOC_KTRACE_MODAGF 3
|
|
#define XFS_ALLOC_KTRACE_BUSY 4
|
|
#define XFS_ALLOC_KTRACE_UNBUSY 5
|
|
#define XFS_ALLOC_KTRACE_BUSYSEARCH 6
|
|
#endif
|
|
|
|
/*
|
|
* 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 */
|
|
|
|
void
|
|
xfs_alloc_mark_busy(xfs_trans_t *tp,
|
|
xfs_agnumber_t agno,
|
|
xfs_agblock_t bno,
|
|
xfs_extlen_t len);
|
|
|
|
void
|
|
xfs_alloc_clear_busy(xfs_trans_t *tp,
|
|
xfs_agnumber_t ag,
|
|
int idx);
|
|
|
|
|
|
#endif /* __KERNEL__ */
|
|
|
|
#endif /* __XFS_ALLOC_H__ */
|