OpenCloudOS-Kernel/fs/xfs/xfs_trans_buf.c

785 lines
21 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (c) 2000-2002,2005 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_mount.h"
#include "xfs_trans.h"
#include "xfs_buf_item.h"
#include "xfs_trans_priv.h"
xfs: event tracing support Convert the old xfs tracing support that could only be used with the out of tree kdb and xfsidbg patches to use the generic event tracer. To use it make sure CONFIG_EVENT_TRACING is enabled and then enable all xfs trace channels by: echo 1 > /sys/kernel/debug/tracing/events/xfs/enable or alternatively enable single events by just doing the same in one event subdirectory, e.g. echo 1 > /sys/kernel/debug/tracing/events/xfs/xfs_ihold/enable or set more complex filters, etc. In Documentation/trace/events.txt all this is desctribed in more detail. To reads the events do a cat /sys/kernel/debug/tracing/trace Compared to the last posting this patch converts the tracing mostly to the one tracepoint per callsite model that other users of the new tracing facility also employ. This allows a very fine-grained control of the tracing, a cleaner output of the traces and also enables the perf tool to use each tracepoint as a virtual performance counter, allowing us to e.g. count how often certain workloads git various spots in XFS. Take a look at http://lwn.net/Articles/346470/ for some examples. Also the btree tracing isn't included at all yet, as it will require additional core tracing features not in mainline yet, I plan to deliver it later. And the really nice thing about this patch is that it actually removes many lines of code while adding this nice functionality: fs/xfs/Makefile | 8 fs/xfs/linux-2.6/xfs_acl.c | 1 fs/xfs/linux-2.6/xfs_aops.c | 52 - fs/xfs/linux-2.6/xfs_aops.h | 2 fs/xfs/linux-2.6/xfs_buf.c | 117 +-- fs/xfs/linux-2.6/xfs_buf.h | 33 fs/xfs/linux-2.6/xfs_fs_subr.c | 3 fs/xfs/linux-2.6/xfs_ioctl.c | 1 fs/xfs/linux-2.6/xfs_ioctl32.c | 1 fs/xfs/linux-2.6/xfs_iops.c | 1 fs/xfs/linux-2.6/xfs_linux.h | 1 fs/xfs/linux-2.6/xfs_lrw.c | 87 -- fs/xfs/linux-2.6/xfs_lrw.h | 45 - fs/xfs/linux-2.6/xfs_super.c | 104 --- fs/xfs/linux-2.6/xfs_super.h | 7 fs/xfs/linux-2.6/xfs_sync.c | 1 fs/xfs/linux-2.6/xfs_trace.c | 75 ++ fs/xfs/linux-2.6/xfs_trace.h | 1369 +++++++++++++++++++++++++++++++++++++++++ fs/xfs/linux-2.6/xfs_vnode.h | 4 fs/xfs/quota/xfs_dquot.c | 110 --- fs/xfs/quota/xfs_dquot.h | 21 fs/xfs/quota/xfs_qm.c | 40 - fs/xfs/quota/xfs_qm_syscalls.c | 4 fs/xfs/support/ktrace.c | 323 --------- fs/xfs/support/ktrace.h | 85 -- fs/xfs/xfs.h | 16 fs/xfs/xfs_ag.h | 14 fs/xfs/xfs_alloc.c | 230 +----- fs/xfs/xfs_alloc.h | 27 fs/xfs/xfs_alloc_btree.c | 1 fs/xfs/xfs_attr.c | 107 --- fs/xfs/xfs_attr.h | 10 fs/xfs/xfs_attr_leaf.c | 14 fs/xfs/xfs_attr_sf.h | 40 - fs/xfs/xfs_bmap.c | 507 +++------------ fs/xfs/xfs_bmap.h | 49 - fs/xfs/xfs_bmap_btree.c | 6 fs/xfs/xfs_btree.c | 5 fs/xfs/xfs_btree_trace.h | 17 fs/xfs/xfs_buf_item.c | 87 -- fs/xfs/xfs_buf_item.h | 20 fs/xfs/xfs_da_btree.c | 3 fs/xfs/xfs_da_btree.h | 7 fs/xfs/xfs_dfrag.c | 2 fs/xfs/xfs_dir2.c | 8 fs/xfs/xfs_dir2_block.c | 20 fs/xfs/xfs_dir2_leaf.c | 21 fs/xfs/xfs_dir2_node.c | 27 fs/xfs/xfs_dir2_sf.c | 26 fs/xfs/xfs_dir2_trace.c | 216 ------ fs/xfs/xfs_dir2_trace.h | 72 -- fs/xfs/xfs_filestream.c | 8 fs/xfs/xfs_fsops.c | 2 fs/xfs/xfs_iget.c | 111 --- fs/xfs/xfs_inode.c | 67 -- fs/xfs/xfs_inode.h | 76 -- fs/xfs/xfs_inode_item.c | 5 fs/xfs/xfs_iomap.c | 85 -- fs/xfs/xfs_iomap.h | 8 fs/xfs/xfs_log.c | 181 +---- fs/xfs/xfs_log_priv.h | 20 fs/xfs/xfs_log_recover.c | 1 fs/xfs/xfs_mount.c | 2 fs/xfs/xfs_quota.h | 8 fs/xfs/xfs_rename.c | 1 fs/xfs/xfs_rtalloc.c | 1 fs/xfs/xfs_rw.c | 3 fs/xfs/xfs_trans.h | 47 + fs/xfs/xfs_trans_buf.c | 62 - fs/xfs/xfs_vnodeops.c | 8 70 files changed, 2151 insertions(+), 2592 deletions(-) Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Alex Elder <aelder@sgi.com>
2009-12-15 07:14:59 +08:00
#include "xfs_trace.h"
/*
* Check to see if a buffer matching the given parameters is already
* a part of the given transaction.
*/
STATIC struct xfs_buf *
xfs_trans_buf_item_match(
struct xfs_trans *tp,
struct xfs_buftarg *target,
struct xfs_buf_map *map,
int nmaps)
{
struct xfs_log_item *lip;
struct xfs_buf_log_item *blip;
int len = 0;
int i;
for (i = 0; i < nmaps; i++)
len += map[i].bm_len;
list_for_each_entry(lip, &tp->t_items, li_trans) {
blip = (struct xfs_buf_log_item *)lip;
if (blip->bli_item.li_type == XFS_LI_BUF &&
blip->bli_buf->b_target == target &&
XFS_BUF_ADDR(blip->bli_buf) == map[0].bm_bn &&
blip->bli_buf->b_length == len) {
ASSERT(blip->bli_buf->b_map_count == nmaps);
return blip->bli_buf;
}
}
return NULL;
}
/*
* Add the locked buffer to the transaction.
*
* The buffer must be locked, and it cannot be associated with any
* transaction.
*
* If the buffer does not yet have a buf log item associated with it,
* then allocate one for it. Then add the buf item to the transaction.
*/
STATIC void
_xfs_trans_bjoin(
struct xfs_trans *tp,
struct xfs_buf *bp,
int reset_recur)
{
struct xfs_buf_log_item *bip;
ASSERT(bp->b_transp == NULL);
/*
* The xfs_buf_log_item pointer is stored in b_log_item. If
* it doesn't have one yet, then allocate one and initialize it.
* The checks to see if one is there are in xfs_buf_item_init().
*/
xfs_buf_item_init(bp, tp->t_mountp);
bip = bp->b_log_item;
ASSERT(!(bip->bli_flags & XFS_BLI_STALE));
ASSERT(!(bip->__bli_format.blf_flags & XFS_BLF_CANCEL));
ASSERT(!(bip->bli_flags & XFS_BLI_LOGGED));
if (reset_recur)
bip->bli_recur = 0;
/*
* Take a reference for this transaction on the buf item.
*/
atomic_inc(&bip->bli_refcount);
/*
* Attach the item to the transaction so we can find it in
* xfs_trans_get_buf() and friends.
*/
xfs_trans_add_item(tp, &bip->bli_item);
bp->b_transp = tp;
}
void
xfs_trans_bjoin(
struct xfs_trans *tp,
struct xfs_buf *bp)
{
_xfs_trans_bjoin(tp, bp, 0);
trace_xfs_trans_bjoin(bp->b_log_item);
}
/*
* Get and lock the buffer for the caller if it is not already
* locked within the given transaction. If it is already locked
* within the transaction, just increment its lock recursion count
* and return a pointer to it.
*
* If the transaction pointer is NULL, make this just a normal
* get_buf() call.
*/
int
xfs_trans_get_buf_map(
struct xfs_trans *tp,
struct xfs_buftarg *target,
struct xfs_buf_map *map,
int nmaps,
xfs_buf_flags_t flags,
struct xfs_buf **bpp)
{
xfs_buf_t *bp;
struct xfs_buf_log_item *bip;
int error;
*bpp = NULL;
if (!tp)
return xfs_buf_get_map(target, map, nmaps, flags, bpp);
/*
* If we find the buffer in the cache with this transaction
* pointer in its b_fsprivate2 field, then we know we already
* have it locked. In this case we just increment the lock
* recursion count and return the buffer to the caller.
*/
bp = xfs_trans_buf_item_match(tp, target, map, nmaps);
if (bp != NULL) {
ASSERT(xfs_buf_islocked(bp));
if (XFS_FORCED_SHUTDOWN(tp->t_mountp)) {
xfs_buf_stale(bp);
bp->b_flags |= XBF_DONE;
}
xfs: event tracing support Convert the old xfs tracing support that could only be used with the out of tree kdb and xfsidbg patches to use the generic event tracer. To use it make sure CONFIG_EVENT_TRACING is enabled and then enable all xfs trace channels by: echo 1 > /sys/kernel/debug/tracing/events/xfs/enable or alternatively enable single events by just doing the same in one event subdirectory, e.g. echo 1 > /sys/kernel/debug/tracing/events/xfs/xfs_ihold/enable or set more complex filters, etc. In Documentation/trace/events.txt all this is desctribed in more detail. To reads the events do a cat /sys/kernel/debug/tracing/trace Compared to the last posting this patch converts the tracing mostly to the one tracepoint per callsite model that other users of the new tracing facility also employ. This allows a very fine-grained control of the tracing, a cleaner output of the traces and also enables the perf tool to use each tracepoint as a virtual performance counter, allowing us to e.g. count how often certain workloads git various spots in XFS. Take a look at http://lwn.net/Articles/346470/ for some examples. Also the btree tracing isn't included at all yet, as it will require additional core tracing features not in mainline yet, I plan to deliver it later. And the really nice thing about this patch is that it actually removes many lines of code while adding this nice functionality: fs/xfs/Makefile | 8 fs/xfs/linux-2.6/xfs_acl.c | 1 fs/xfs/linux-2.6/xfs_aops.c | 52 - fs/xfs/linux-2.6/xfs_aops.h | 2 fs/xfs/linux-2.6/xfs_buf.c | 117 +-- fs/xfs/linux-2.6/xfs_buf.h | 33 fs/xfs/linux-2.6/xfs_fs_subr.c | 3 fs/xfs/linux-2.6/xfs_ioctl.c | 1 fs/xfs/linux-2.6/xfs_ioctl32.c | 1 fs/xfs/linux-2.6/xfs_iops.c | 1 fs/xfs/linux-2.6/xfs_linux.h | 1 fs/xfs/linux-2.6/xfs_lrw.c | 87 -- fs/xfs/linux-2.6/xfs_lrw.h | 45 - fs/xfs/linux-2.6/xfs_super.c | 104 --- fs/xfs/linux-2.6/xfs_super.h | 7 fs/xfs/linux-2.6/xfs_sync.c | 1 fs/xfs/linux-2.6/xfs_trace.c | 75 ++ fs/xfs/linux-2.6/xfs_trace.h | 1369 +++++++++++++++++++++++++++++++++++++++++ fs/xfs/linux-2.6/xfs_vnode.h | 4 fs/xfs/quota/xfs_dquot.c | 110 --- fs/xfs/quota/xfs_dquot.h | 21 fs/xfs/quota/xfs_qm.c | 40 - fs/xfs/quota/xfs_qm_syscalls.c | 4 fs/xfs/support/ktrace.c | 323 --------- fs/xfs/support/ktrace.h | 85 -- fs/xfs/xfs.h | 16 fs/xfs/xfs_ag.h | 14 fs/xfs/xfs_alloc.c | 230 +----- fs/xfs/xfs_alloc.h | 27 fs/xfs/xfs_alloc_btree.c | 1 fs/xfs/xfs_attr.c | 107 --- fs/xfs/xfs_attr.h | 10 fs/xfs/xfs_attr_leaf.c | 14 fs/xfs/xfs_attr_sf.h | 40 - fs/xfs/xfs_bmap.c | 507 +++------------ fs/xfs/xfs_bmap.h | 49 - fs/xfs/xfs_bmap_btree.c | 6 fs/xfs/xfs_btree.c | 5 fs/xfs/xfs_btree_trace.h | 17 fs/xfs/xfs_buf_item.c | 87 -- fs/xfs/xfs_buf_item.h | 20 fs/xfs/xfs_da_btree.c | 3 fs/xfs/xfs_da_btree.h | 7 fs/xfs/xfs_dfrag.c | 2 fs/xfs/xfs_dir2.c | 8 fs/xfs/xfs_dir2_block.c | 20 fs/xfs/xfs_dir2_leaf.c | 21 fs/xfs/xfs_dir2_node.c | 27 fs/xfs/xfs_dir2_sf.c | 26 fs/xfs/xfs_dir2_trace.c | 216 ------ fs/xfs/xfs_dir2_trace.h | 72 -- fs/xfs/xfs_filestream.c | 8 fs/xfs/xfs_fsops.c | 2 fs/xfs/xfs_iget.c | 111 --- fs/xfs/xfs_inode.c | 67 -- fs/xfs/xfs_inode.h | 76 -- fs/xfs/xfs_inode_item.c | 5 fs/xfs/xfs_iomap.c | 85 -- fs/xfs/xfs_iomap.h | 8 fs/xfs/xfs_log.c | 181 +---- fs/xfs/xfs_log_priv.h | 20 fs/xfs/xfs_log_recover.c | 1 fs/xfs/xfs_mount.c | 2 fs/xfs/xfs_quota.h | 8 fs/xfs/xfs_rename.c | 1 fs/xfs/xfs_rtalloc.c | 1 fs/xfs/xfs_rw.c | 3 fs/xfs/xfs_trans.h | 47 + fs/xfs/xfs_trans_buf.c | 62 - fs/xfs/xfs_vnodeops.c | 8 70 files changed, 2151 insertions(+), 2592 deletions(-) Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Alex Elder <aelder@sgi.com>
2009-12-15 07:14:59 +08:00
ASSERT(bp->b_transp == tp);
bip = bp->b_log_item;
ASSERT(bip != NULL);
ASSERT(atomic_read(&bip->bli_refcount) > 0);
bip->bli_recur++;
xfs: event tracing support Convert the old xfs tracing support that could only be used with the out of tree kdb and xfsidbg patches to use the generic event tracer. To use it make sure CONFIG_EVENT_TRACING is enabled and then enable all xfs trace channels by: echo 1 > /sys/kernel/debug/tracing/events/xfs/enable or alternatively enable single events by just doing the same in one event subdirectory, e.g. echo 1 > /sys/kernel/debug/tracing/events/xfs/xfs_ihold/enable or set more complex filters, etc. In Documentation/trace/events.txt all this is desctribed in more detail. To reads the events do a cat /sys/kernel/debug/tracing/trace Compared to the last posting this patch converts the tracing mostly to the one tracepoint per callsite model that other users of the new tracing facility also employ. This allows a very fine-grained control of the tracing, a cleaner output of the traces and also enables the perf tool to use each tracepoint as a virtual performance counter, allowing us to e.g. count how often certain workloads git various spots in XFS. Take a look at http://lwn.net/Articles/346470/ for some examples. Also the btree tracing isn't included at all yet, as it will require additional core tracing features not in mainline yet, I plan to deliver it later. And the really nice thing about this patch is that it actually removes many lines of code while adding this nice functionality: fs/xfs/Makefile | 8 fs/xfs/linux-2.6/xfs_acl.c | 1 fs/xfs/linux-2.6/xfs_aops.c | 52 - fs/xfs/linux-2.6/xfs_aops.h | 2 fs/xfs/linux-2.6/xfs_buf.c | 117 +-- fs/xfs/linux-2.6/xfs_buf.h | 33 fs/xfs/linux-2.6/xfs_fs_subr.c | 3 fs/xfs/linux-2.6/xfs_ioctl.c | 1 fs/xfs/linux-2.6/xfs_ioctl32.c | 1 fs/xfs/linux-2.6/xfs_iops.c | 1 fs/xfs/linux-2.6/xfs_linux.h | 1 fs/xfs/linux-2.6/xfs_lrw.c | 87 -- fs/xfs/linux-2.6/xfs_lrw.h | 45 - fs/xfs/linux-2.6/xfs_super.c | 104 --- fs/xfs/linux-2.6/xfs_super.h | 7 fs/xfs/linux-2.6/xfs_sync.c | 1 fs/xfs/linux-2.6/xfs_trace.c | 75 ++ fs/xfs/linux-2.6/xfs_trace.h | 1369 +++++++++++++++++++++++++++++++++++++++++ fs/xfs/linux-2.6/xfs_vnode.h | 4 fs/xfs/quota/xfs_dquot.c | 110 --- fs/xfs/quota/xfs_dquot.h | 21 fs/xfs/quota/xfs_qm.c | 40 - fs/xfs/quota/xfs_qm_syscalls.c | 4 fs/xfs/support/ktrace.c | 323 --------- fs/xfs/support/ktrace.h | 85 -- fs/xfs/xfs.h | 16 fs/xfs/xfs_ag.h | 14 fs/xfs/xfs_alloc.c | 230 +----- fs/xfs/xfs_alloc.h | 27 fs/xfs/xfs_alloc_btree.c | 1 fs/xfs/xfs_attr.c | 107 --- fs/xfs/xfs_attr.h | 10 fs/xfs/xfs_attr_leaf.c | 14 fs/xfs/xfs_attr_sf.h | 40 - fs/xfs/xfs_bmap.c | 507 +++------------ fs/xfs/xfs_bmap.h | 49 - fs/xfs/xfs_bmap_btree.c | 6 fs/xfs/xfs_btree.c | 5 fs/xfs/xfs_btree_trace.h | 17 fs/xfs/xfs_buf_item.c | 87 -- fs/xfs/xfs_buf_item.h | 20 fs/xfs/xfs_da_btree.c | 3 fs/xfs/xfs_da_btree.h | 7 fs/xfs/xfs_dfrag.c | 2 fs/xfs/xfs_dir2.c | 8 fs/xfs/xfs_dir2_block.c | 20 fs/xfs/xfs_dir2_leaf.c | 21 fs/xfs/xfs_dir2_node.c | 27 fs/xfs/xfs_dir2_sf.c | 26 fs/xfs/xfs_dir2_trace.c | 216 ------ fs/xfs/xfs_dir2_trace.h | 72 -- fs/xfs/xfs_filestream.c | 8 fs/xfs/xfs_fsops.c | 2 fs/xfs/xfs_iget.c | 111 --- fs/xfs/xfs_inode.c | 67 -- fs/xfs/xfs_inode.h | 76 -- fs/xfs/xfs_inode_item.c | 5 fs/xfs/xfs_iomap.c | 85 -- fs/xfs/xfs_iomap.h | 8 fs/xfs/xfs_log.c | 181 +---- fs/xfs/xfs_log_priv.h | 20 fs/xfs/xfs_log_recover.c | 1 fs/xfs/xfs_mount.c | 2 fs/xfs/xfs_quota.h | 8 fs/xfs/xfs_rename.c | 1 fs/xfs/xfs_rtalloc.c | 1 fs/xfs/xfs_rw.c | 3 fs/xfs/xfs_trans.h | 47 + fs/xfs/xfs_trans_buf.c | 62 - fs/xfs/xfs_vnodeops.c | 8 70 files changed, 2151 insertions(+), 2592 deletions(-) Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Alex Elder <aelder@sgi.com>
2009-12-15 07:14:59 +08:00
trace_xfs_trans_get_buf_recur(bip);
*bpp = bp;
return 0;
}
error = xfs_buf_get_map(target, map, nmaps, flags, &bp);
if (error)
return error;
ASSERT(!bp->b_error);
_xfs_trans_bjoin(tp, bp, 1);
trace_xfs_trans_get_buf(bp->b_log_item);
*bpp = bp;
return 0;
}
/*
* Get and lock the superblock buffer of this file system for the
* given transaction.
*
* We don't need to use incore_match() here, because the superblock
* buffer is a private buffer which we keep a pointer to in the
* mount structure.
*/
xfs_buf_t *
xfs_trans_getsb(
xfs_trans_t *tp,
struct xfs_mount *mp)
{
xfs_buf_t *bp;
struct xfs_buf_log_item *bip;
/*
* Default to just trying to lock the superblock buffer
* if tp is NULL.
*/
if (tp == NULL)
return xfs_getsb(mp);
/*
* If the superblock buffer already has this transaction
* pointer in its b_fsprivate2 field, then we know we already
* have it locked. In this case we just increment the lock
* recursion count and return the buffer to the caller.
*/
bp = mp->m_sb_bp;
if (bp->b_transp == tp) {
bip = bp->b_log_item;
ASSERT(bip != NULL);
ASSERT(atomic_read(&bip->bli_refcount) > 0);
bip->bli_recur++;
xfs: event tracing support Convert the old xfs tracing support that could only be used with the out of tree kdb and xfsidbg patches to use the generic event tracer. To use it make sure CONFIG_EVENT_TRACING is enabled and then enable all xfs trace channels by: echo 1 > /sys/kernel/debug/tracing/events/xfs/enable or alternatively enable single events by just doing the same in one event subdirectory, e.g. echo 1 > /sys/kernel/debug/tracing/events/xfs/xfs_ihold/enable or set more complex filters, etc. In Documentation/trace/events.txt all this is desctribed in more detail. To reads the events do a cat /sys/kernel/debug/tracing/trace Compared to the last posting this patch converts the tracing mostly to the one tracepoint per callsite model that other users of the new tracing facility also employ. This allows a very fine-grained control of the tracing, a cleaner output of the traces and also enables the perf tool to use each tracepoint as a virtual performance counter, allowing us to e.g. count how often certain workloads git various spots in XFS. Take a look at http://lwn.net/Articles/346470/ for some examples. Also the btree tracing isn't included at all yet, as it will require additional core tracing features not in mainline yet, I plan to deliver it later. And the really nice thing about this patch is that it actually removes many lines of code while adding this nice functionality: fs/xfs/Makefile | 8 fs/xfs/linux-2.6/xfs_acl.c | 1 fs/xfs/linux-2.6/xfs_aops.c | 52 - fs/xfs/linux-2.6/xfs_aops.h | 2 fs/xfs/linux-2.6/xfs_buf.c | 117 +-- fs/xfs/linux-2.6/xfs_buf.h | 33 fs/xfs/linux-2.6/xfs_fs_subr.c | 3 fs/xfs/linux-2.6/xfs_ioctl.c | 1 fs/xfs/linux-2.6/xfs_ioctl32.c | 1 fs/xfs/linux-2.6/xfs_iops.c | 1 fs/xfs/linux-2.6/xfs_linux.h | 1 fs/xfs/linux-2.6/xfs_lrw.c | 87 -- fs/xfs/linux-2.6/xfs_lrw.h | 45 - fs/xfs/linux-2.6/xfs_super.c | 104 --- fs/xfs/linux-2.6/xfs_super.h | 7 fs/xfs/linux-2.6/xfs_sync.c | 1 fs/xfs/linux-2.6/xfs_trace.c | 75 ++ fs/xfs/linux-2.6/xfs_trace.h | 1369 +++++++++++++++++++++++++++++++++++++++++ fs/xfs/linux-2.6/xfs_vnode.h | 4 fs/xfs/quota/xfs_dquot.c | 110 --- fs/xfs/quota/xfs_dquot.h | 21 fs/xfs/quota/xfs_qm.c | 40 - fs/xfs/quota/xfs_qm_syscalls.c | 4 fs/xfs/support/ktrace.c | 323 --------- fs/xfs/support/ktrace.h | 85 -- fs/xfs/xfs.h | 16 fs/xfs/xfs_ag.h | 14 fs/xfs/xfs_alloc.c | 230 +----- fs/xfs/xfs_alloc.h | 27 fs/xfs/xfs_alloc_btree.c | 1 fs/xfs/xfs_attr.c | 107 --- fs/xfs/xfs_attr.h | 10 fs/xfs/xfs_attr_leaf.c | 14 fs/xfs/xfs_attr_sf.h | 40 - fs/xfs/xfs_bmap.c | 507 +++------------ fs/xfs/xfs_bmap.h | 49 - fs/xfs/xfs_bmap_btree.c | 6 fs/xfs/xfs_btree.c | 5 fs/xfs/xfs_btree_trace.h | 17 fs/xfs/xfs_buf_item.c | 87 -- fs/xfs/xfs_buf_item.h | 20 fs/xfs/xfs_da_btree.c | 3 fs/xfs/xfs_da_btree.h | 7 fs/xfs/xfs_dfrag.c | 2 fs/xfs/xfs_dir2.c | 8 fs/xfs/xfs_dir2_block.c | 20 fs/xfs/xfs_dir2_leaf.c | 21 fs/xfs/xfs_dir2_node.c | 27 fs/xfs/xfs_dir2_sf.c | 26 fs/xfs/xfs_dir2_trace.c | 216 ------ fs/xfs/xfs_dir2_trace.h | 72 -- fs/xfs/xfs_filestream.c | 8 fs/xfs/xfs_fsops.c | 2 fs/xfs/xfs_iget.c | 111 --- fs/xfs/xfs_inode.c | 67 -- fs/xfs/xfs_inode.h | 76 -- fs/xfs/xfs_inode_item.c | 5 fs/xfs/xfs_iomap.c | 85 -- fs/xfs/xfs_iomap.h | 8 fs/xfs/xfs_log.c | 181 +---- fs/xfs/xfs_log_priv.h | 20 fs/xfs/xfs_log_recover.c | 1 fs/xfs/xfs_mount.c | 2 fs/xfs/xfs_quota.h | 8 fs/xfs/xfs_rename.c | 1 fs/xfs/xfs_rtalloc.c | 1 fs/xfs/xfs_rw.c | 3 fs/xfs/xfs_trans.h | 47 + fs/xfs/xfs_trans_buf.c | 62 - fs/xfs/xfs_vnodeops.c | 8 70 files changed, 2151 insertions(+), 2592 deletions(-) Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Alex Elder <aelder@sgi.com>
2009-12-15 07:14:59 +08:00
trace_xfs_trans_getsb_recur(bip);
return bp;
}
bp = xfs_getsb(mp);
if (bp == NULL)
return NULL;
_xfs_trans_bjoin(tp, bp, 1);
trace_xfs_trans_getsb(bp->b_log_item);
return bp;
}
/*
* Get and lock the buffer for the caller if it is not already
* locked within the given transaction. If it has not yet been
* read in, read it from disk. If it is already locked
* within the transaction and already read in, just increment its
* lock recursion count and return a pointer to it.
*
* If the transaction pointer is NULL, make this just a normal
* read_buf() call.
*/
int
xfs_trans_read_buf_map(
struct xfs_mount *mp,
struct xfs_trans *tp,
struct xfs_buftarg *target,
struct xfs_buf_map *map,
int nmaps,
xfs_buf_flags_t flags,
struct xfs_buf **bpp,
const struct xfs_buf_ops *ops)
{
struct xfs_buf *bp = NULL;
struct xfs_buf_log_item *bip;
int error;
*bpp = NULL;
/*
* If we find the buffer in the cache with this transaction
* pointer in its b_fsprivate2 field, then we know we already
* have it locked. If it is already read in we just increment
* the lock recursion count and return the buffer to the caller.
* If the buffer is not yet read in, then we read it in, increment
* the lock recursion count, and return it to the caller.
*/
if (tp)
bp = xfs_trans_buf_item_match(tp, target, map, nmaps);
if (bp) {
ASSERT(xfs_buf_islocked(bp));
ASSERT(bp->b_transp == tp);
ASSERT(bp->b_log_item != NULL);
ASSERT(!bp->b_error);
ASSERT(bp->b_flags & XBF_DONE);
/*
* We never locked this buf ourselves, so we shouldn't
* brelse it either. Just get out.
*/
if (XFS_FORCED_SHUTDOWN(mp)) {
xfs: event tracing support Convert the old xfs tracing support that could only be used with the out of tree kdb and xfsidbg patches to use the generic event tracer. To use it make sure CONFIG_EVENT_TRACING is enabled and then enable all xfs trace channels by: echo 1 > /sys/kernel/debug/tracing/events/xfs/enable or alternatively enable single events by just doing the same in one event subdirectory, e.g. echo 1 > /sys/kernel/debug/tracing/events/xfs/xfs_ihold/enable or set more complex filters, etc. In Documentation/trace/events.txt all this is desctribed in more detail. To reads the events do a cat /sys/kernel/debug/tracing/trace Compared to the last posting this patch converts the tracing mostly to the one tracepoint per callsite model that other users of the new tracing facility also employ. This allows a very fine-grained control of the tracing, a cleaner output of the traces and also enables the perf tool to use each tracepoint as a virtual performance counter, allowing us to e.g. count how often certain workloads git various spots in XFS. Take a look at http://lwn.net/Articles/346470/ for some examples. Also the btree tracing isn't included at all yet, as it will require additional core tracing features not in mainline yet, I plan to deliver it later. And the really nice thing about this patch is that it actually removes many lines of code while adding this nice functionality: fs/xfs/Makefile | 8 fs/xfs/linux-2.6/xfs_acl.c | 1 fs/xfs/linux-2.6/xfs_aops.c | 52 - fs/xfs/linux-2.6/xfs_aops.h | 2 fs/xfs/linux-2.6/xfs_buf.c | 117 +-- fs/xfs/linux-2.6/xfs_buf.h | 33 fs/xfs/linux-2.6/xfs_fs_subr.c | 3 fs/xfs/linux-2.6/xfs_ioctl.c | 1 fs/xfs/linux-2.6/xfs_ioctl32.c | 1 fs/xfs/linux-2.6/xfs_iops.c | 1 fs/xfs/linux-2.6/xfs_linux.h | 1 fs/xfs/linux-2.6/xfs_lrw.c | 87 -- fs/xfs/linux-2.6/xfs_lrw.h | 45 - fs/xfs/linux-2.6/xfs_super.c | 104 --- fs/xfs/linux-2.6/xfs_super.h | 7 fs/xfs/linux-2.6/xfs_sync.c | 1 fs/xfs/linux-2.6/xfs_trace.c | 75 ++ fs/xfs/linux-2.6/xfs_trace.h | 1369 +++++++++++++++++++++++++++++++++++++++++ fs/xfs/linux-2.6/xfs_vnode.h | 4 fs/xfs/quota/xfs_dquot.c | 110 --- fs/xfs/quota/xfs_dquot.h | 21 fs/xfs/quota/xfs_qm.c | 40 - fs/xfs/quota/xfs_qm_syscalls.c | 4 fs/xfs/support/ktrace.c | 323 --------- fs/xfs/support/ktrace.h | 85 -- fs/xfs/xfs.h | 16 fs/xfs/xfs_ag.h | 14 fs/xfs/xfs_alloc.c | 230 +----- fs/xfs/xfs_alloc.h | 27 fs/xfs/xfs_alloc_btree.c | 1 fs/xfs/xfs_attr.c | 107 --- fs/xfs/xfs_attr.h | 10 fs/xfs/xfs_attr_leaf.c | 14 fs/xfs/xfs_attr_sf.h | 40 - fs/xfs/xfs_bmap.c | 507 +++------------ fs/xfs/xfs_bmap.h | 49 - fs/xfs/xfs_bmap_btree.c | 6 fs/xfs/xfs_btree.c | 5 fs/xfs/xfs_btree_trace.h | 17 fs/xfs/xfs_buf_item.c | 87 -- fs/xfs/xfs_buf_item.h | 20 fs/xfs/xfs_da_btree.c | 3 fs/xfs/xfs_da_btree.h | 7 fs/xfs/xfs_dfrag.c | 2 fs/xfs/xfs_dir2.c | 8 fs/xfs/xfs_dir2_block.c | 20 fs/xfs/xfs_dir2_leaf.c | 21 fs/xfs/xfs_dir2_node.c | 27 fs/xfs/xfs_dir2_sf.c | 26 fs/xfs/xfs_dir2_trace.c | 216 ------ fs/xfs/xfs_dir2_trace.h | 72 -- fs/xfs/xfs_filestream.c | 8 fs/xfs/xfs_fsops.c | 2 fs/xfs/xfs_iget.c | 111 --- fs/xfs/xfs_inode.c | 67 -- fs/xfs/xfs_inode.h | 76 -- fs/xfs/xfs_inode_item.c | 5 fs/xfs/xfs_iomap.c | 85 -- fs/xfs/xfs_iomap.h | 8 fs/xfs/xfs_log.c | 181 +---- fs/xfs/xfs_log_priv.h | 20 fs/xfs/xfs_log_recover.c | 1 fs/xfs/xfs_mount.c | 2 fs/xfs/xfs_quota.h | 8 fs/xfs/xfs_rename.c | 1 fs/xfs/xfs_rtalloc.c | 1 fs/xfs/xfs_rw.c | 3 fs/xfs/xfs_trans.h | 47 + fs/xfs/xfs_trans_buf.c | 62 - fs/xfs/xfs_vnodeops.c | 8 70 files changed, 2151 insertions(+), 2592 deletions(-) Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Alex Elder <aelder@sgi.com>
2009-12-15 07:14:59 +08:00
trace_xfs_trans_read_buf_shut(bp, _RET_IP_);
return -EIO;
}
/*
* Check if the caller is trying to read a buffer that is
* already attached to the transaction yet has no buffer ops
* assigned. Ops are usually attached when the buffer is
* attached to the transaction, or by the read caller if
* special circumstances. That didn't happen, which is not
* how this is supposed to go.
*
* If the buffer passes verification we'll let this go, but if
* not we have to shut down. Let the transaction cleanup code
* release this buffer when it kills the tranaction.
*/
ASSERT(bp->b_ops != NULL);
error = xfs_buf_reverify(bp, ops);
if (error) {
xfs_buf_ioerror_alert(bp, __return_address);
if (tp->t_flags & XFS_TRANS_DIRTY)
xfs_force_shutdown(tp->t_mountp,
SHUTDOWN_META_IO_ERROR);
/* bad CRC means corrupted metadata */
if (error == -EFSBADCRC)
error = -EFSCORRUPTED;
return error;
}
bip = bp->b_log_item;
bip->bli_recur++;
ASSERT(atomic_read(&bip->bli_refcount) > 0);
xfs: event tracing support Convert the old xfs tracing support that could only be used with the out of tree kdb and xfsidbg patches to use the generic event tracer. To use it make sure CONFIG_EVENT_TRACING is enabled and then enable all xfs trace channels by: echo 1 > /sys/kernel/debug/tracing/events/xfs/enable or alternatively enable single events by just doing the same in one event subdirectory, e.g. echo 1 > /sys/kernel/debug/tracing/events/xfs/xfs_ihold/enable or set more complex filters, etc. In Documentation/trace/events.txt all this is desctribed in more detail. To reads the events do a cat /sys/kernel/debug/tracing/trace Compared to the last posting this patch converts the tracing mostly to the one tracepoint per callsite model that other users of the new tracing facility also employ. This allows a very fine-grained control of the tracing, a cleaner output of the traces and also enables the perf tool to use each tracepoint as a virtual performance counter, allowing us to e.g. count how often certain workloads git various spots in XFS. Take a look at http://lwn.net/Articles/346470/ for some examples. Also the btree tracing isn't included at all yet, as it will require additional core tracing features not in mainline yet, I plan to deliver it later. And the really nice thing about this patch is that it actually removes many lines of code while adding this nice functionality: fs/xfs/Makefile | 8 fs/xfs/linux-2.6/xfs_acl.c | 1 fs/xfs/linux-2.6/xfs_aops.c | 52 - fs/xfs/linux-2.6/xfs_aops.h | 2 fs/xfs/linux-2.6/xfs_buf.c | 117 +-- fs/xfs/linux-2.6/xfs_buf.h | 33 fs/xfs/linux-2.6/xfs_fs_subr.c | 3 fs/xfs/linux-2.6/xfs_ioctl.c | 1 fs/xfs/linux-2.6/xfs_ioctl32.c | 1 fs/xfs/linux-2.6/xfs_iops.c | 1 fs/xfs/linux-2.6/xfs_linux.h | 1 fs/xfs/linux-2.6/xfs_lrw.c | 87 -- fs/xfs/linux-2.6/xfs_lrw.h | 45 - fs/xfs/linux-2.6/xfs_super.c | 104 --- fs/xfs/linux-2.6/xfs_super.h | 7 fs/xfs/linux-2.6/xfs_sync.c | 1 fs/xfs/linux-2.6/xfs_trace.c | 75 ++ fs/xfs/linux-2.6/xfs_trace.h | 1369 +++++++++++++++++++++++++++++++++++++++++ fs/xfs/linux-2.6/xfs_vnode.h | 4 fs/xfs/quota/xfs_dquot.c | 110 --- fs/xfs/quota/xfs_dquot.h | 21 fs/xfs/quota/xfs_qm.c | 40 - fs/xfs/quota/xfs_qm_syscalls.c | 4 fs/xfs/support/ktrace.c | 323 --------- fs/xfs/support/ktrace.h | 85 -- fs/xfs/xfs.h | 16 fs/xfs/xfs_ag.h | 14 fs/xfs/xfs_alloc.c | 230 +----- fs/xfs/xfs_alloc.h | 27 fs/xfs/xfs_alloc_btree.c | 1 fs/xfs/xfs_attr.c | 107 --- fs/xfs/xfs_attr.h | 10 fs/xfs/xfs_attr_leaf.c | 14 fs/xfs/xfs_attr_sf.h | 40 - fs/xfs/xfs_bmap.c | 507 +++------------ fs/xfs/xfs_bmap.h | 49 - fs/xfs/xfs_bmap_btree.c | 6 fs/xfs/xfs_btree.c | 5 fs/xfs/xfs_btree_trace.h | 17 fs/xfs/xfs_buf_item.c | 87 -- fs/xfs/xfs_buf_item.h | 20 fs/xfs/xfs_da_btree.c | 3 fs/xfs/xfs_da_btree.h | 7 fs/xfs/xfs_dfrag.c | 2 fs/xfs/xfs_dir2.c | 8 fs/xfs/xfs_dir2_block.c | 20 fs/xfs/xfs_dir2_leaf.c | 21 fs/xfs/xfs_dir2_node.c | 27 fs/xfs/xfs_dir2_sf.c | 26 fs/xfs/xfs_dir2_trace.c | 216 ------ fs/xfs/xfs_dir2_trace.h | 72 -- fs/xfs/xfs_filestream.c | 8 fs/xfs/xfs_fsops.c | 2 fs/xfs/xfs_iget.c | 111 --- fs/xfs/xfs_inode.c | 67 -- fs/xfs/xfs_inode.h | 76 -- fs/xfs/xfs_inode_item.c | 5 fs/xfs/xfs_iomap.c | 85 -- fs/xfs/xfs_iomap.h | 8 fs/xfs/xfs_log.c | 181 +---- fs/xfs/xfs_log_priv.h | 20 fs/xfs/xfs_log_recover.c | 1 fs/xfs/xfs_mount.c | 2 fs/xfs/xfs_quota.h | 8 fs/xfs/xfs_rename.c | 1 fs/xfs/xfs_rtalloc.c | 1 fs/xfs/xfs_rw.c | 3 fs/xfs/xfs_trans.h | 47 + fs/xfs/xfs_trans_buf.c | 62 - fs/xfs/xfs_vnodeops.c | 8 70 files changed, 2151 insertions(+), 2592 deletions(-) Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Alex Elder <aelder@sgi.com>
2009-12-15 07:14:59 +08:00
trace_xfs_trans_read_buf_recur(bip);
ASSERT(bp->b_ops != NULL || ops == NULL);
*bpp = bp;
return 0;
}
error = xfs_buf_read_map(target, map, nmaps, flags, &bp, ops,
__return_address);
switch (error) {
case 0:
break;
default:
if (tp && (tp->t_flags & XFS_TRANS_DIRTY))
xfs_force_shutdown(tp->t_mountp, SHUTDOWN_META_IO_ERROR);
/* fall through */
case -ENOMEM:
case -EAGAIN:
return error;
}
if (XFS_FORCED_SHUTDOWN(mp)) {
xfs_buf_relse(bp);
trace_xfs_trans_read_buf_shut(bp, _RET_IP_);
return -EIO;
}
if (tp) {
_xfs_trans_bjoin(tp, bp, 1);
trace_xfs_trans_read_buf(bp->b_log_item);
}
ASSERT(bp->b_ops != NULL || ops == NULL);
*bpp = bp;
return 0;
}
/* Has this buffer been dirtied by anyone? */
bool
xfs_trans_buf_is_dirty(
struct xfs_buf *bp)
{
struct xfs_buf_log_item *bip = bp->b_log_item;
if (!bip)
return false;
ASSERT(bip->bli_item.li_type == XFS_LI_BUF);
return test_bit(XFS_LI_DIRTY, &bip->bli_item.li_flags);
}
/*
* Release a buffer previously joined to the transaction. If the buffer is
* modified within this transaction, decrement the recursion count but do not
* release the buffer even if the count goes to 0. If the buffer is not modified
* within the transaction, decrement the recursion count and release the buffer
* if the recursion count goes to 0.
*
* If the buffer is to be released and it was not already dirty before this
* transaction began, then also free the buf_log_item associated with it.
*
* If the transaction pointer is NULL, this is a normal xfs_buf_relse() call.
*/
void
xfs_trans_brelse(
struct xfs_trans *tp,
struct xfs_buf *bp)
{
struct xfs_buf_log_item *bip = bp->b_log_item;
ASSERT(bp->b_transp == tp);
if (!tp) {
xfs_buf_relse(bp);
return;
}
trace_xfs_trans_brelse(bip);
ASSERT(bip->bli_item.li_type == XFS_LI_BUF);
ASSERT(atomic_read(&bip->bli_refcount) > 0);
/*
* If the release is for a recursive lookup, then decrement the count
* and return.
*/
if (bip->bli_recur > 0) {
bip->bli_recur--;
return;
}
/*
* If the buffer is invalidated or dirty in this transaction, we can't
* release it until we commit.
*/
if (test_bit(XFS_LI_DIRTY, &bip->bli_item.li_flags))
return;
xfs: event tracing support Convert the old xfs tracing support that could only be used with the out of tree kdb and xfsidbg patches to use the generic event tracer. To use it make sure CONFIG_EVENT_TRACING is enabled and then enable all xfs trace channels by: echo 1 > /sys/kernel/debug/tracing/events/xfs/enable or alternatively enable single events by just doing the same in one event subdirectory, e.g. echo 1 > /sys/kernel/debug/tracing/events/xfs/xfs_ihold/enable or set more complex filters, etc. In Documentation/trace/events.txt all this is desctribed in more detail. To reads the events do a cat /sys/kernel/debug/tracing/trace Compared to the last posting this patch converts the tracing mostly to the one tracepoint per callsite model that other users of the new tracing facility also employ. This allows a very fine-grained control of the tracing, a cleaner output of the traces and also enables the perf tool to use each tracepoint as a virtual performance counter, allowing us to e.g. count how often certain workloads git various spots in XFS. Take a look at http://lwn.net/Articles/346470/ for some examples. Also the btree tracing isn't included at all yet, as it will require additional core tracing features not in mainline yet, I plan to deliver it later. And the really nice thing about this patch is that it actually removes many lines of code while adding this nice functionality: fs/xfs/Makefile | 8 fs/xfs/linux-2.6/xfs_acl.c | 1 fs/xfs/linux-2.6/xfs_aops.c | 52 - fs/xfs/linux-2.6/xfs_aops.h | 2 fs/xfs/linux-2.6/xfs_buf.c | 117 +-- fs/xfs/linux-2.6/xfs_buf.h | 33 fs/xfs/linux-2.6/xfs_fs_subr.c | 3 fs/xfs/linux-2.6/xfs_ioctl.c | 1 fs/xfs/linux-2.6/xfs_ioctl32.c | 1 fs/xfs/linux-2.6/xfs_iops.c | 1 fs/xfs/linux-2.6/xfs_linux.h | 1 fs/xfs/linux-2.6/xfs_lrw.c | 87 -- fs/xfs/linux-2.6/xfs_lrw.h | 45 - fs/xfs/linux-2.6/xfs_super.c | 104 --- fs/xfs/linux-2.6/xfs_super.h | 7 fs/xfs/linux-2.6/xfs_sync.c | 1 fs/xfs/linux-2.6/xfs_trace.c | 75 ++ fs/xfs/linux-2.6/xfs_trace.h | 1369 +++++++++++++++++++++++++++++++++++++++++ fs/xfs/linux-2.6/xfs_vnode.h | 4 fs/xfs/quota/xfs_dquot.c | 110 --- fs/xfs/quota/xfs_dquot.h | 21 fs/xfs/quota/xfs_qm.c | 40 - fs/xfs/quota/xfs_qm_syscalls.c | 4 fs/xfs/support/ktrace.c | 323 --------- fs/xfs/support/ktrace.h | 85 -- fs/xfs/xfs.h | 16 fs/xfs/xfs_ag.h | 14 fs/xfs/xfs_alloc.c | 230 +----- fs/xfs/xfs_alloc.h | 27 fs/xfs/xfs_alloc_btree.c | 1 fs/xfs/xfs_attr.c | 107 --- fs/xfs/xfs_attr.h | 10 fs/xfs/xfs_attr_leaf.c | 14 fs/xfs/xfs_attr_sf.h | 40 - fs/xfs/xfs_bmap.c | 507 +++------------ fs/xfs/xfs_bmap.h | 49 - fs/xfs/xfs_bmap_btree.c | 6 fs/xfs/xfs_btree.c | 5 fs/xfs/xfs_btree_trace.h | 17 fs/xfs/xfs_buf_item.c | 87 -- fs/xfs/xfs_buf_item.h | 20 fs/xfs/xfs_da_btree.c | 3 fs/xfs/xfs_da_btree.h | 7 fs/xfs/xfs_dfrag.c | 2 fs/xfs/xfs_dir2.c | 8 fs/xfs/xfs_dir2_block.c | 20 fs/xfs/xfs_dir2_leaf.c | 21 fs/xfs/xfs_dir2_node.c | 27 fs/xfs/xfs_dir2_sf.c | 26 fs/xfs/xfs_dir2_trace.c | 216 ------ fs/xfs/xfs_dir2_trace.h | 72 -- fs/xfs/xfs_filestream.c | 8 fs/xfs/xfs_fsops.c | 2 fs/xfs/xfs_iget.c | 111 --- fs/xfs/xfs_inode.c | 67 -- fs/xfs/xfs_inode.h | 76 -- fs/xfs/xfs_inode_item.c | 5 fs/xfs/xfs_iomap.c | 85 -- fs/xfs/xfs_iomap.h | 8 fs/xfs/xfs_log.c | 181 +---- fs/xfs/xfs_log_priv.h | 20 fs/xfs/xfs_log_recover.c | 1 fs/xfs/xfs_mount.c | 2 fs/xfs/xfs_quota.h | 8 fs/xfs/xfs_rename.c | 1 fs/xfs/xfs_rtalloc.c | 1 fs/xfs/xfs_rw.c | 3 fs/xfs/xfs_trans.h | 47 + fs/xfs/xfs_trans_buf.c | 62 - fs/xfs/xfs_vnodeops.c | 8 70 files changed, 2151 insertions(+), 2592 deletions(-) Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Alex Elder <aelder@sgi.com>
2009-12-15 07:14:59 +08:00
if (bip->bli_flags & XFS_BLI_STALE)
return;
/*
* Unlink the log item from the transaction and clear the hold flag, if
* set. We wouldn't want the next user of the buffer to get confused.
*/
ASSERT(!(bip->bli_flags & XFS_BLI_LOGGED));
xfs_trans_del_item(&bip->bli_item);
bip->bli_flags &= ~XFS_BLI_HOLD;
xfs: refactor xfs_buf_log_item reference count handling The xfs_buf_log_item structure has a reference counter with slightly tricky semantics. In the common case, a buffer is logged and committed in a transaction, committed to the on-disk log (added to the AIL) and then finally written back and removed from the AIL. The bli refcount covers two potentially overlapping timeframes: 1. the bli is held in an active transaction 2. the bli is pinned by the log The caveat to this approach is that the reference counter does not purely dictate the lifetime of the bli. IOW, when a dirty buffer is physically logged and unpinned, the bli refcount may go to zero as the log item is inserted into the AIL. Only once the buffer is written back can the bli finally be freed. The above semantics means that it is not enough for the various refcount decrementing contexts to release the bli on decrement to zero. xfs_trans_brelse(), transaction commit (->iop_unlock()) and unpin (->iop_unpin()) must all drop the associated reference and make additional checks to determine if the current context is responsible for freeing the item. For example, if a transaction holds but does not dirty a particular bli, the commit may drop the refcount to zero. If the bli itself is clean, it is also not AIL resident and must be freed at this time. The same is true for xfs_trans_brelse(). If the transaction dirties a bli and then aborts or an unpin results in an abort due to a log I/O error, the last reference count holder is expected to explicitly remove the item from the AIL and release it (since an abort means filesystem shutdown and metadata writeback will never occur). This leads to fairly complex checks being replicated in a few different places. Since ->iop_unlock() and xfs_trans_brelse() are nearly identical, refactor the logic into a common helper that implements and documents the semantics in one place. This patch does not change behavior. Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2018-09-29 11:45:26 +08:00
/* drop the reference to the bli */
xfs_buf_item_put(bip);
bp->b_transp = NULL;
xfs_buf_relse(bp);
}
/*
* Mark the buffer as not needing to be unlocked when the buf item's
xfs: split iop_unlock The iop_unlock method is called when comitting or cancelling a transaction. In the latter case, the transaction may or may not be aborted. While there is no known problem with the current code in practice, this implementation is limited in that any log item implementation that might want to differentiate between a commit and a cancellation must rely on the aborted state. The aborted bit is only set when the cancelled transaction is dirty, however. This means that there is no way to distinguish between a commit and a clean transaction cancellation. For example, intent log items currently rely on this distinction. The log item is either transferred to the CIL on commit or released on transaction cancel. There is currently no possibility for a clean intent log item in a transaction, but if that state is ever introduced a cancel of such a transaction will immediately result in memory leaks of the associated log item(s). This is an interface deficiency and landmine. To clean this up, replace the iop_unlock method with an iop_release method that is specific to transaction cancel. The existing iop_committing method occurs at the same time as iop_unlock in the commit path and there is no need for two separate callbacks here. Overload the iop_committing method with the current commit time iop_unlock implementations to eliminate the need for the latter and further simplify the interface. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-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>
2019-06-29 10:27:32 +08:00
* iop_committing() routine is called. The buffer must already be locked
* and associated with the given transaction.
*/
/* ARGSUSED */
void
xfs_trans_bhold(
xfs_trans_t *tp,
xfs_buf_t *bp)
{
struct xfs_buf_log_item *bip = bp->b_log_item;
ASSERT(bp->b_transp == tp);
ASSERT(bip != NULL);
ASSERT(!(bip->bli_flags & XFS_BLI_STALE));
ASSERT(!(bip->__bli_format.blf_flags & XFS_BLF_CANCEL));
ASSERT(atomic_read(&bip->bli_refcount) > 0);
bip->bli_flags |= XFS_BLI_HOLD;
xfs: event tracing support Convert the old xfs tracing support that could only be used with the out of tree kdb and xfsidbg patches to use the generic event tracer. To use it make sure CONFIG_EVENT_TRACING is enabled and then enable all xfs trace channels by: echo 1 > /sys/kernel/debug/tracing/events/xfs/enable or alternatively enable single events by just doing the same in one event subdirectory, e.g. echo 1 > /sys/kernel/debug/tracing/events/xfs/xfs_ihold/enable or set more complex filters, etc. In Documentation/trace/events.txt all this is desctribed in more detail. To reads the events do a cat /sys/kernel/debug/tracing/trace Compared to the last posting this patch converts the tracing mostly to the one tracepoint per callsite model that other users of the new tracing facility also employ. This allows a very fine-grained control of the tracing, a cleaner output of the traces and also enables the perf tool to use each tracepoint as a virtual performance counter, allowing us to e.g. count how often certain workloads git various spots in XFS. Take a look at http://lwn.net/Articles/346470/ for some examples. Also the btree tracing isn't included at all yet, as it will require additional core tracing features not in mainline yet, I plan to deliver it later. And the really nice thing about this patch is that it actually removes many lines of code while adding this nice functionality: fs/xfs/Makefile | 8 fs/xfs/linux-2.6/xfs_acl.c | 1 fs/xfs/linux-2.6/xfs_aops.c | 52 - fs/xfs/linux-2.6/xfs_aops.h | 2 fs/xfs/linux-2.6/xfs_buf.c | 117 +-- fs/xfs/linux-2.6/xfs_buf.h | 33 fs/xfs/linux-2.6/xfs_fs_subr.c | 3 fs/xfs/linux-2.6/xfs_ioctl.c | 1 fs/xfs/linux-2.6/xfs_ioctl32.c | 1 fs/xfs/linux-2.6/xfs_iops.c | 1 fs/xfs/linux-2.6/xfs_linux.h | 1 fs/xfs/linux-2.6/xfs_lrw.c | 87 -- fs/xfs/linux-2.6/xfs_lrw.h | 45 - fs/xfs/linux-2.6/xfs_super.c | 104 --- fs/xfs/linux-2.6/xfs_super.h | 7 fs/xfs/linux-2.6/xfs_sync.c | 1 fs/xfs/linux-2.6/xfs_trace.c | 75 ++ fs/xfs/linux-2.6/xfs_trace.h | 1369 +++++++++++++++++++++++++++++++++++++++++ fs/xfs/linux-2.6/xfs_vnode.h | 4 fs/xfs/quota/xfs_dquot.c | 110 --- fs/xfs/quota/xfs_dquot.h | 21 fs/xfs/quota/xfs_qm.c | 40 - fs/xfs/quota/xfs_qm_syscalls.c | 4 fs/xfs/support/ktrace.c | 323 --------- fs/xfs/support/ktrace.h | 85 -- fs/xfs/xfs.h | 16 fs/xfs/xfs_ag.h | 14 fs/xfs/xfs_alloc.c | 230 +----- fs/xfs/xfs_alloc.h | 27 fs/xfs/xfs_alloc_btree.c | 1 fs/xfs/xfs_attr.c | 107 --- fs/xfs/xfs_attr.h | 10 fs/xfs/xfs_attr_leaf.c | 14 fs/xfs/xfs_attr_sf.h | 40 - fs/xfs/xfs_bmap.c | 507 +++------------ fs/xfs/xfs_bmap.h | 49 - fs/xfs/xfs_bmap_btree.c | 6 fs/xfs/xfs_btree.c | 5 fs/xfs/xfs_btree_trace.h | 17 fs/xfs/xfs_buf_item.c | 87 -- fs/xfs/xfs_buf_item.h | 20 fs/xfs/xfs_da_btree.c | 3 fs/xfs/xfs_da_btree.h | 7 fs/xfs/xfs_dfrag.c | 2 fs/xfs/xfs_dir2.c | 8 fs/xfs/xfs_dir2_block.c | 20 fs/xfs/xfs_dir2_leaf.c | 21 fs/xfs/xfs_dir2_node.c | 27 fs/xfs/xfs_dir2_sf.c | 26 fs/xfs/xfs_dir2_trace.c | 216 ------ fs/xfs/xfs_dir2_trace.h | 72 -- fs/xfs/xfs_filestream.c | 8 fs/xfs/xfs_fsops.c | 2 fs/xfs/xfs_iget.c | 111 --- fs/xfs/xfs_inode.c | 67 -- fs/xfs/xfs_inode.h | 76 -- fs/xfs/xfs_inode_item.c | 5 fs/xfs/xfs_iomap.c | 85 -- fs/xfs/xfs_iomap.h | 8 fs/xfs/xfs_log.c | 181 +---- fs/xfs/xfs_log_priv.h | 20 fs/xfs/xfs_log_recover.c | 1 fs/xfs/xfs_mount.c | 2 fs/xfs/xfs_quota.h | 8 fs/xfs/xfs_rename.c | 1 fs/xfs/xfs_rtalloc.c | 1 fs/xfs/xfs_rw.c | 3 fs/xfs/xfs_trans.h | 47 + fs/xfs/xfs_trans_buf.c | 62 - fs/xfs/xfs_vnodeops.c | 8 70 files changed, 2151 insertions(+), 2592 deletions(-) Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Alex Elder <aelder@sgi.com>
2009-12-15 07:14:59 +08:00
trace_xfs_trans_bhold(bip);
}
/*
* Cancel the previous buffer hold request made on this buffer
* for this transaction.
*/
void
xfs_trans_bhold_release(
xfs_trans_t *tp,
xfs_buf_t *bp)
{
struct xfs_buf_log_item *bip = bp->b_log_item;
ASSERT(bp->b_transp == tp);
ASSERT(bip != NULL);
ASSERT(!(bip->bli_flags & XFS_BLI_STALE));
ASSERT(!(bip->__bli_format.blf_flags & XFS_BLF_CANCEL));
ASSERT(atomic_read(&bip->bli_refcount) > 0);
ASSERT(bip->bli_flags & XFS_BLI_HOLD);
xfs: event tracing support Convert the old xfs tracing support that could only be used with the out of tree kdb and xfsidbg patches to use the generic event tracer. To use it make sure CONFIG_EVENT_TRACING is enabled and then enable all xfs trace channels by: echo 1 > /sys/kernel/debug/tracing/events/xfs/enable or alternatively enable single events by just doing the same in one event subdirectory, e.g. echo 1 > /sys/kernel/debug/tracing/events/xfs/xfs_ihold/enable or set more complex filters, etc. In Documentation/trace/events.txt all this is desctribed in more detail. To reads the events do a cat /sys/kernel/debug/tracing/trace Compared to the last posting this patch converts the tracing mostly to the one tracepoint per callsite model that other users of the new tracing facility also employ. This allows a very fine-grained control of the tracing, a cleaner output of the traces and also enables the perf tool to use each tracepoint as a virtual performance counter, allowing us to e.g. count how often certain workloads git various spots in XFS. Take a look at http://lwn.net/Articles/346470/ for some examples. Also the btree tracing isn't included at all yet, as it will require additional core tracing features not in mainline yet, I plan to deliver it later. And the really nice thing about this patch is that it actually removes many lines of code while adding this nice functionality: fs/xfs/Makefile | 8 fs/xfs/linux-2.6/xfs_acl.c | 1 fs/xfs/linux-2.6/xfs_aops.c | 52 - fs/xfs/linux-2.6/xfs_aops.h | 2 fs/xfs/linux-2.6/xfs_buf.c | 117 +-- fs/xfs/linux-2.6/xfs_buf.h | 33 fs/xfs/linux-2.6/xfs_fs_subr.c | 3 fs/xfs/linux-2.6/xfs_ioctl.c | 1 fs/xfs/linux-2.6/xfs_ioctl32.c | 1 fs/xfs/linux-2.6/xfs_iops.c | 1 fs/xfs/linux-2.6/xfs_linux.h | 1 fs/xfs/linux-2.6/xfs_lrw.c | 87 -- fs/xfs/linux-2.6/xfs_lrw.h | 45 - fs/xfs/linux-2.6/xfs_super.c | 104 --- fs/xfs/linux-2.6/xfs_super.h | 7 fs/xfs/linux-2.6/xfs_sync.c | 1 fs/xfs/linux-2.6/xfs_trace.c | 75 ++ fs/xfs/linux-2.6/xfs_trace.h | 1369 +++++++++++++++++++++++++++++++++++++++++ fs/xfs/linux-2.6/xfs_vnode.h | 4 fs/xfs/quota/xfs_dquot.c | 110 --- fs/xfs/quota/xfs_dquot.h | 21 fs/xfs/quota/xfs_qm.c | 40 - fs/xfs/quota/xfs_qm_syscalls.c | 4 fs/xfs/support/ktrace.c | 323 --------- fs/xfs/support/ktrace.h | 85 -- fs/xfs/xfs.h | 16 fs/xfs/xfs_ag.h | 14 fs/xfs/xfs_alloc.c | 230 +----- fs/xfs/xfs_alloc.h | 27 fs/xfs/xfs_alloc_btree.c | 1 fs/xfs/xfs_attr.c | 107 --- fs/xfs/xfs_attr.h | 10 fs/xfs/xfs_attr_leaf.c | 14 fs/xfs/xfs_attr_sf.h | 40 - fs/xfs/xfs_bmap.c | 507 +++------------ fs/xfs/xfs_bmap.h | 49 - fs/xfs/xfs_bmap_btree.c | 6 fs/xfs/xfs_btree.c | 5 fs/xfs/xfs_btree_trace.h | 17 fs/xfs/xfs_buf_item.c | 87 -- fs/xfs/xfs_buf_item.h | 20 fs/xfs/xfs_da_btree.c | 3 fs/xfs/xfs_da_btree.h | 7 fs/xfs/xfs_dfrag.c | 2 fs/xfs/xfs_dir2.c | 8 fs/xfs/xfs_dir2_block.c | 20 fs/xfs/xfs_dir2_leaf.c | 21 fs/xfs/xfs_dir2_node.c | 27 fs/xfs/xfs_dir2_sf.c | 26 fs/xfs/xfs_dir2_trace.c | 216 ------ fs/xfs/xfs_dir2_trace.h | 72 -- fs/xfs/xfs_filestream.c | 8 fs/xfs/xfs_fsops.c | 2 fs/xfs/xfs_iget.c | 111 --- fs/xfs/xfs_inode.c | 67 -- fs/xfs/xfs_inode.h | 76 -- fs/xfs/xfs_inode_item.c | 5 fs/xfs/xfs_iomap.c | 85 -- fs/xfs/xfs_iomap.h | 8 fs/xfs/xfs_log.c | 181 +---- fs/xfs/xfs_log_priv.h | 20 fs/xfs/xfs_log_recover.c | 1 fs/xfs/xfs_mount.c | 2 fs/xfs/xfs_quota.h | 8 fs/xfs/xfs_rename.c | 1 fs/xfs/xfs_rtalloc.c | 1 fs/xfs/xfs_rw.c | 3 fs/xfs/xfs_trans.h | 47 + fs/xfs/xfs_trans_buf.c | 62 - fs/xfs/xfs_vnodeops.c | 8 70 files changed, 2151 insertions(+), 2592 deletions(-) Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Alex Elder <aelder@sgi.com>
2009-12-15 07:14:59 +08:00
bip->bli_flags &= ~XFS_BLI_HOLD;
xfs: event tracing support Convert the old xfs tracing support that could only be used with the out of tree kdb and xfsidbg patches to use the generic event tracer. To use it make sure CONFIG_EVENT_TRACING is enabled and then enable all xfs trace channels by: echo 1 > /sys/kernel/debug/tracing/events/xfs/enable or alternatively enable single events by just doing the same in one event subdirectory, e.g. echo 1 > /sys/kernel/debug/tracing/events/xfs/xfs_ihold/enable or set more complex filters, etc. In Documentation/trace/events.txt all this is desctribed in more detail. To reads the events do a cat /sys/kernel/debug/tracing/trace Compared to the last posting this patch converts the tracing mostly to the one tracepoint per callsite model that other users of the new tracing facility also employ. This allows a very fine-grained control of the tracing, a cleaner output of the traces and also enables the perf tool to use each tracepoint as a virtual performance counter, allowing us to e.g. count how often certain workloads git various spots in XFS. Take a look at http://lwn.net/Articles/346470/ for some examples. Also the btree tracing isn't included at all yet, as it will require additional core tracing features not in mainline yet, I plan to deliver it later. And the really nice thing about this patch is that it actually removes many lines of code while adding this nice functionality: fs/xfs/Makefile | 8 fs/xfs/linux-2.6/xfs_acl.c | 1 fs/xfs/linux-2.6/xfs_aops.c | 52 - fs/xfs/linux-2.6/xfs_aops.h | 2 fs/xfs/linux-2.6/xfs_buf.c | 117 +-- fs/xfs/linux-2.6/xfs_buf.h | 33 fs/xfs/linux-2.6/xfs_fs_subr.c | 3 fs/xfs/linux-2.6/xfs_ioctl.c | 1 fs/xfs/linux-2.6/xfs_ioctl32.c | 1 fs/xfs/linux-2.6/xfs_iops.c | 1 fs/xfs/linux-2.6/xfs_linux.h | 1 fs/xfs/linux-2.6/xfs_lrw.c | 87 -- fs/xfs/linux-2.6/xfs_lrw.h | 45 - fs/xfs/linux-2.6/xfs_super.c | 104 --- fs/xfs/linux-2.6/xfs_super.h | 7 fs/xfs/linux-2.6/xfs_sync.c | 1 fs/xfs/linux-2.6/xfs_trace.c | 75 ++ fs/xfs/linux-2.6/xfs_trace.h | 1369 +++++++++++++++++++++++++++++++++++++++++ fs/xfs/linux-2.6/xfs_vnode.h | 4 fs/xfs/quota/xfs_dquot.c | 110 --- fs/xfs/quota/xfs_dquot.h | 21 fs/xfs/quota/xfs_qm.c | 40 - fs/xfs/quota/xfs_qm_syscalls.c | 4 fs/xfs/support/ktrace.c | 323 --------- fs/xfs/support/ktrace.h | 85 -- fs/xfs/xfs.h | 16 fs/xfs/xfs_ag.h | 14 fs/xfs/xfs_alloc.c | 230 +----- fs/xfs/xfs_alloc.h | 27 fs/xfs/xfs_alloc_btree.c | 1 fs/xfs/xfs_attr.c | 107 --- fs/xfs/xfs_attr.h | 10 fs/xfs/xfs_attr_leaf.c | 14 fs/xfs/xfs_attr_sf.h | 40 - fs/xfs/xfs_bmap.c | 507 +++------------ fs/xfs/xfs_bmap.h | 49 - fs/xfs/xfs_bmap_btree.c | 6 fs/xfs/xfs_btree.c | 5 fs/xfs/xfs_btree_trace.h | 17 fs/xfs/xfs_buf_item.c | 87 -- fs/xfs/xfs_buf_item.h | 20 fs/xfs/xfs_da_btree.c | 3 fs/xfs/xfs_da_btree.h | 7 fs/xfs/xfs_dfrag.c | 2 fs/xfs/xfs_dir2.c | 8 fs/xfs/xfs_dir2_block.c | 20 fs/xfs/xfs_dir2_leaf.c | 21 fs/xfs/xfs_dir2_node.c | 27 fs/xfs/xfs_dir2_sf.c | 26 fs/xfs/xfs_dir2_trace.c | 216 ------ fs/xfs/xfs_dir2_trace.h | 72 -- fs/xfs/xfs_filestream.c | 8 fs/xfs/xfs_fsops.c | 2 fs/xfs/xfs_iget.c | 111 --- fs/xfs/xfs_inode.c | 67 -- fs/xfs/xfs_inode.h | 76 -- fs/xfs/xfs_inode_item.c | 5 fs/xfs/xfs_iomap.c | 85 -- fs/xfs/xfs_iomap.h | 8 fs/xfs/xfs_log.c | 181 +---- fs/xfs/xfs_log_priv.h | 20 fs/xfs/xfs_log_recover.c | 1 fs/xfs/xfs_mount.c | 2 fs/xfs/xfs_quota.h | 8 fs/xfs/xfs_rename.c | 1 fs/xfs/xfs_rtalloc.c | 1 fs/xfs/xfs_rw.c | 3 fs/xfs/xfs_trans.h | 47 + fs/xfs/xfs_trans_buf.c | 62 - fs/xfs/xfs_vnodeops.c | 8 70 files changed, 2151 insertions(+), 2592 deletions(-) Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Alex Elder <aelder@sgi.com>
2009-12-15 07:14:59 +08:00
trace_xfs_trans_bhold_release(bip);
}
/*
* Mark a buffer dirty in the transaction.
*/
void
xfs_trans_dirty_buf(
struct xfs_trans *tp,
struct xfs_buf *bp)
{
struct xfs_buf_log_item *bip = bp->b_log_item;
ASSERT(bp->b_transp == tp);
ASSERT(bip != NULL);
/*
* Mark the buffer as needing to be written out eventually,
* and set its iodone function to remove the buffer's buf log
* item from the AIL and free it when the buffer is flushed
* to disk.
*/
bp->b_flags |= XBF_DONE;
ASSERT(atomic_read(&bip->bli_refcount) > 0);
/*
* If we invalidated the buffer within this transaction, then
* cancel the invalidation now that we're dirtying the buffer
* again. There are no races with the code in xfs_buf_item_unpin(),
* because we have a reference to the buffer this entire time.
*/
if (bip->bli_flags & XFS_BLI_STALE) {
bip->bli_flags &= ~XFS_BLI_STALE;
ASSERT(bp->b_flags & XBF_STALE);
bp->b_flags &= ~XBF_STALE;
bip->__bli_format.blf_flags &= ~XFS_BLF_CANCEL;
}
bip->bli_flags |= XFS_BLI_DIRTY | XFS_BLI_LOGGED;
tp->t_flags |= XFS_TRANS_DIRTY;
set_bit(XFS_LI_DIRTY, &bip->bli_item.li_flags);
}
/*
* This is called to mark bytes first through last inclusive of the given
* buffer as needing to be logged when the transaction is committed.
* The buffer must already be associated with the given transaction.
*
* First and last are numbers relative to the beginning of this buffer,
* so the first byte in the buffer is numbered 0 regardless of the
* value of b_blkno.
*/
void
xfs_trans_log_buf(
struct xfs_trans *tp,
struct xfs_buf *bp,
uint first,
uint last)
{
struct xfs_buf_log_item *bip = bp->b_log_item;
ASSERT(first <= last && last < BBTOB(bp->b_length));
ASSERT(!(bip->bli_flags & XFS_BLI_ORDERED));
xfs_trans_dirty_buf(tp, bp);
trace_xfs_trans_log_buf(bip);
xfs_buf_item_log(bip, first, last);
}
/*
xfs: on-stack delayed write buffer lists Queue delwri buffers on a local on-stack list instead of a per-buftarg one, and write back the buffers per-process instead of by waking up xfsbufd. This is now easily doable given that we have very few places left that write delwri buffers: - log recovery: Only done at mount time, and already forcing out the buffers synchronously using xfs_flush_buftarg - quotacheck: Same story. - dquot reclaim: Writes out dirty dquots on the LRU under memory pressure. We might want to look into doing more of this via xfsaild, but it's already more optimal than the synchronous inode reclaim that writes each buffer synchronously. - xfsaild: This is the main beneficiary of the change. By keeping a local list of buffers to write we reduce latency of writing out buffers, and more importably we can remove all the delwri list promotions which were hitting the buffer cache hard under sustained metadata loads. The implementation is very straight forward - xfs_buf_delwri_queue now gets a new list_head pointer that it adds the delwri buffers to, and all callers need to eventually submit the list using xfs_buf_delwi_submit or xfs_buf_delwi_submit_nowait. Buffers that already are on a delwri list are skipped in xfs_buf_delwri_queue, assuming they already are on another delwri list. The biggest change to pass down the buffer list was done to the AIL pushing. Now that we operate on buffers the trylock, push and pushbuf log item methods are merged into a single push routine, which tries to lock the item, and if possible add the buffer that needs writeback to the buffer list. This leads to much simpler code than the previous split but requires the individual IOP_PUSH instances to unlock and reacquire the AIL around calls to blocking routines. Given that xfsailds now also handle writing out buffers, the conditions for log forcing and the sleep times needed some small changes. The most important one is that we consider an AIL busy as long we still have buffers to push, and the other one is that we do increment the pushed LSN for buffers that are under flushing at this moment, but still count them towards the stuck items for restart purposes. Without this we could hammer on stuck items without ever forcing the log and not make progress under heavy random delete workloads on fast flash storage devices. [ Dave Chinner: - rebase on previous patches. - improved comments for XBF_DELWRI_Q handling - fix XBF_ASYNC handling in queue submission (test 106 failure) - rename delwri submit function buffer list parameters for clarity - xfs_efd_item_push() should return XFS_ITEM_PINNED ] Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Mark Tinguely <tinguely@sgi.com> Signed-off-by: Ben Myers <bpm@sgi.com>
2012-04-23 13:58:39 +08:00
* Invalidate a buffer that is being used within a transaction.
*
* Typically this is because the blocks in the buffer are being freed, so we
* need to prevent it from being written out when we're done. Allowing it
* to be written again might overwrite data in the free blocks if they are
* reallocated to a file.
*
xfs: on-stack delayed write buffer lists Queue delwri buffers on a local on-stack list instead of a per-buftarg one, and write back the buffers per-process instead of by waking up xfsbufd. This is now easily doable given that we have very few places left that write delwri buffers: - log recovery: Only done at mount time, and already forcing out the buffers synchronously using xfs_flush_buftarg - quotacheck: Same story. - dquot reclaim: Writes out dirty dquots on the LRU under memory pressure. We might want to look into doing more of this via xfsaild, but it's already more optimal than the synchronous inode reclaim that writes each buffer synchronously. - xfsaild: This is the main beneficiary of the change. By keeping a local list of buffers to write we reduce latency of writing out buffers, and more importably we can remove all the delwri list promotions which were hitting the buffer cache hard under sustained metadata loads. The implementation is very straight forward - xfs_buf_delwri_queue now gets a new list_head pointer that it adds the delwri buffers to, and all callers need to eventually submit the list using xfs_buf_delwi_submit or xfs_buf_delwi_submit_nowait. Buffers that already are on a delwri list are skipped in xfs_buf_delwri_queue, assuming they already are on another delwri list. The biggest change to pass down the buffer list was done to the AIL pushing. Now that we operate on buffers the trylock, push and pushbuf log item methods are merged into a single push routine, which tries to lock the item, and if possible add the buffer that needs writeback to the buffer list. This leads to much simpler code than the previous split but requires the individual IOP_PUSH instances to unlock and reacquire the AIL around calls to blocking routines. Given that xfsailds now also handle writing out buffers, the conditions for log forcing and the sleep times needed some small changes. The most important one is that we consider an AIL busy as long we still have buffers to push, and the other one is that we do increment the pushed LSN for buffers that are under flushing at this moment, but still count them towards the stuck items for restart purposes. Without this we could hammer on stuck items without ever forcing the log and not make progress under heavy random delete workloads on fast flash storage devices. [ Dave Chinner: - rebase on previous patches. - improved comments for XBF_DELWRI_Q handling - fix XBF_ASYNC handling in queue submission (test 106 failure) - rename delwri submit function buffer list parameters for clarity - xfs_efd_item_push() should return XFS_ITEM_PINNED ] Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Mark Tinguely <tinguely@sgi.com> Signed-off-by: Ben Myers <bpm@sgi.com>
2012-04-23 13:58:39 +08:00
* We prevent the buffer from being written out by marking it stale. We can't
* get rid of the buf log item at this point because the buffer may still be
* pinned by another transaction. If that is the case, then we'll wait until
* the buffer is committed to disk for the last time (we can tell by the ref
* count) and free it in xfs_buf_item_unpin(). Until that happens we will
* keep the buffer locked so that the buffer and buf log item are not reused.
*
* We also set the XFS_BLF_CANCEL flag in the buf log format structure and log
* the buf item. This will be used at recovery time to determine that copies
* of the buffer in the log before this should not be replayed.
*
* We mark the item descriptor and the transaction dirty so that we'll hold
* the buffer until after the commit.
*
* Since we're invalidating the buffer, we also clear the state about which
* parts of the buffer have been logged. We also clear the flag indicating
* that this is an inode buffer since the data in the buffer will no longer
* be valid.
*
* We set the stale bit in the buffer as well since we're getting rid of it.
*/
void
xfs_trans_binval(
xfs_trans_t *tp,
xfs_buf_t *bp)
{
struct xfs_buf_log_item *bip = bp->b_log_item;
int i;
ASSERT(bp->b_transp == tp);
ASSERT(bip != NULL);
ASSERT(atomic_read(&bip->bli_refcount) > 0);
xfs: event tracing support Convert the old xfs tracing support that could only be used with the out of tree kdb and xfsidbg patches to use the generic event tracer. To use it make sure CONFIG_EVENT_TRACING is enabled and then enable all xfs trace channels by: echo 1 > /sys/kernel/debug/tracing/events/xfs/enable or alternatively enable single events by just doing the same in one event subdirectory, e.g. echo 1 > /sys/kernel/debug/tracing/events/xfs/xfs_ihold/enable or set more complex filters, etc. In Documentation/trace/events.txt all this is desctribed in more detail. To reads the events do a cat /sys/kernel/debug/tracing/trace Compared to the last posting this patch converts the tracing mostly to the one tracepoint per callsite model that other users of the new tracing facility also employ. This allows a very fine-grained control of the tracing, a cleaner output of the traces and also enables the perf tool to use each tracepoint as a virtual performance counter, allowing us to e.g. count how often certain workloads git various spots in XFS. Take a look at http://lwn.net/Articles/346470/ for some examples. Also the btree tracing isn't included at all yet, as it will require additional core tracing features not in mainline yet, I plan to deliver it later. And the really nice thing about this patch is that it actually removes many lines of code while adding this nice functionality: fs/xfs/Makefile | 8 fs/xfs/linux-2.6/xfs_acl.c | 1 fs/xfs/linux-2.6/xfs_aops.c | 52 - fs/xfs/linux-2.6/xfs_aops.h | 2 fs/xfs/linux-2.6/xfs_buf.c | 117 +-- fs/xfs/linux-2.6/xfs_buf.h | 33 fs/xfs/linux-2.6/xfs_fs_subr.c | 3 fs/xfs/linux-2.6/xfs_ioctl.c | 1 fs/xfs/linux-2.6/xfs_ioctl32.c | 1 fs/xfs/linux-2.6/xfs_iops.c | 1 fs/xfs/linux-2.6/xfs_linux.h | 1 fs/xfs/linux-2.6/xfs_lrw.c | 87 -- fs/xfs/linux-2.6/xfs_lrw.h | 45 - fs/xfs/linux-2.6/xfs_super.c | 104 --- fs/xfs/linux-2.6/xfs_super.h | 7 fs/xfs/linux-2.6/xfs_sync.c | 1 fs/xfs/linux-2.6/xfs_trace.c | 75 ++ fs/xfs/linux-2.6/xfs_trace.h | 1369 +++++++++++++++++++++++++++++++++++++++++ fs/xfs/linux-2.6/xfs_vnode.h | 4 fs/xfs/quota/xfs_dquot.c | 110 --- fs/xfs/quota/xfs_dquot.h | 21 fs/xfs/quota/xfs_qm.c | 40 - fs/xfs/quota/xfs_qm_syscalls.c | 4 fs/xfs/support/ktrace.c | 323 --------- fs/xfs/support/ktrace.h | 85 -- fs/xfs/xfs.h | 16 fs/xfs/xfs_ag.h | 14 fs/xfs/xfs_alloc.c | 230 +----- fs/xfs/xfs_alloc.h | 27 fs/xfs/xfs_alloc_btree.c | 1 fs/xfs/xfs_attr.c | 107 --- fs/xfs/xfs_attr.h | 10 fs/xfs/xfs_attr_leaf.c | 14 fs/xfs/xfs_attr_sf.h | 40 - fs/xfs/xfs_bmap.c | 507 +++------------ fs/xfs/xfs_bmap.h | 49 - fs/xfs/xfs_bmap_btree.c | 6 fs/xfs/xfs_btree.c | 5 fs/xfs/xfs_btree_trace.h | 17 fs/xfs/xfs_buf_item.c | 87 -- fs/xfs/xfs_buf_item.h | 20 fs/xfs/xfs_da_btree.c | 3 fs/xfs/xfs_da_btree.h | 7 fs/xfs/xfs_dfrag.c | 2 fs/xfs/xfs_dir2.c | 8 fs/xfs/xfs_dir2_block.c | 20 fs/xfs/xfs_dir2_leaf.c | 21 fs/xfs/xfs_dir2_node.c | 27 fs/xfs/xfs_dir2_sf.c | 26 fs/xfs/xfs_dir2_trace.c | 216 ------ fs/xfs/xfs_dir2_trace.h | 72 -- fs/xfs/xfs_filestream.c | 8 fs/xfs/xfs_fsops.c | 2 fs/xfs/xfs_iget.c | 111 --- fs/xfs/xfs_inode.c | 67 -- fs/xfs/xfs_inode.h | 76 -- fs/xfs/xfs_inode_item.c | 5 fs/xfs/xfs_iomap.c | 85 -- fs/xfs/xfs_iomap.h | 8 fs/xfs/xfs_log.c | 181 +---- fs/xfs/xfs_log_priv.h | 20 fs/xfs/xfs_log_recover.c | 1 fs/xfs/xfs_mount.c | 2 fs/xfs/xfs_quota.h | 8 fs/xfs/xfs_rename.c | 1 fs/xfs/xfs_rtalloc.c | 1 fs/xfs/xfs_rw.c | 3 fs/xfs/xfs_trans.h | 47 + fs/xfs/xfs_trans_buf.c | 62 - fs/xfs/xfs_vnodeops.c | 8 70 files changed, 2151 insertions(+), 2592 deletions(-) Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Alex Elder <aelder@sgi.com>
2009-12-15 07:14:59 +08:00
trace_xfs_trans_binval(bip);
if (bip->bli_flags & XFS_BLI_STALE) {
/*
* If the buffer is already invalidated, then
* just return.
*/
ASSERT(bp->b_flags & XBF_STALE);
ASSERT(!(bip->bli_flags & (XFS_BLI_LOGGED | XFS_BLI_DIRTY)));
ASSERT(!(bip->__bli_format.blf_flags & XFS_BLF_INODE_BUF));
ASSERT(!(bip->__bli_format.blf_flags & XFS_BLFT_MASK));
ASSERT(bip->__bli_format.blf_flags & XFS_BLF_CANCEL);
ASSERT(test_bit(XFS_LI_DIRTY, &bip->bli_item.li_flags));
ASSERT(tp->t_flags & XFS_TRANS_DIRTY);
return;
}
xfs_buf_stale(bp);
xfs: on-stack delayed write buffer lists Queue delwri buffers on a local on-stack list instead of a per-buftarg one, and write back the buffers per-process instead of by waking up xfsbufd. This is now easily doable given that we have very few places left that write delwri buffers: - log recovery: Only done at mount time, and already forcing out the buffers synchronously using xfs_flush_buftarg - quotacheck: Same story. - dquot reclaim: Writes out dirty dquots on the LRU under memory pressure. We might want to look into doing more of this via xfsaild, but it's already more optimal than the synchronous inode reclaim that writes each buffer synchronously. - xfsaild: This is the main beneficiary of the change. By keeping a local list of buffers to write we reduce latency of writing out buffers, and more importably we can remove all the delwri list promotions which were hitting the buffer cache hard under sustained metadata loads. The implementation is very straight forward - xfs_buf_delwri_queue now gets a new list_head pointer that it adds the delwri buffers to, and all callers need to eventually submit the list using xfs_buf_delwi_submit or xfs_buf_delwi_submit_nowait. Buffers that already are on a delwri list are skipped in xfs_buf_delwri_queue, assuming they already are on another delwri list. The biggest change to pass down the buffer list was done to the AIL pushing. Now that we operate on buffers the trylock, push and pushbuf log item methods are merged into a single push routine, which tries to lock the item, and if possible add the buffer that needs writeback to the buffer list. This leads to much simpler code than the previous split but requires the individual IOP_PUSH instances to unlock and reacquire the AIL around calls to blocking routines. Given that xfsailds now also handle writing out buffers, the conditions for log forcing and the sleep times needed some small changes. The most important one is that we consider an AIL busy as long we still have buffers to push, and the other one is that we do increment the pushed LSN for buffers that are under flushing at this moment, but still count them towards the stuck items for restart purposes. Without this we could hammer on stuck items without ever forcing the log and not make progress under heavy random delete workloads on fast flash storage devices. [ Dave Chinner: - rebase on previous patches. - improved comments for XBF_DELWRI_Q handling - fix XBF_ASYNC handling in queue submission (test 106 failure) - rename delwri submit function buffer list parameters for clarity - xfs_efd_item_push() should return XFS_ITEM_PINNED ] Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Mark Tinguely <tinguely@sgi.com> Signed-off-by: Ben Myers <bpm@sgi.com>
2012-04-23 13:58:39 +08:00
bip->bli_flags |= XFS_BLI_STALE;
xfs: Ensure inode allocation buffers are fully replayed With delayed logging, we can get inode allocation buffers in the same transaction inode unlink buffers. We don't currently mark inode allocation buffers in the log, so inode unlink buffers take precedence over allocation buffers. The result is that when they are combined into the same checkpoint, only the unlinked inode chain fields are replayed, resulting in uninitialised inode buffers being detected when the next inode modification is replayed. To fix this, we need to ensure that we do not set the inode buffer flag in the buffer log item format flags if the inode allocation has not already hit the log. To avoid requiring a change to log recovery, we really need to make this a modification that relies only on in-memory sate. We can do this by checking during buffer log formatting (while the CIL cannot be flushed) if we are still in the same sequence when we commit the unlink transaction as the inode allocation transaction. If we are, then we do not add the inode buffer flag to the buffer log format item flags. This means the entire buffer will be replayed, not just the unlinked fields. We do this while CIL flusheѕ are locked out to ensure that we don't race with the sequence numbers changing and hence fail to put the inode buffer flag in the buffer format flags when we really need to. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Alex Elder <aelder@sgi.com>
2010-05-20 21:19:42 +08:00
bip->bli_flags &= ~(XFS_BLI_INODE_BUF | XFS_BLI_LOGGED | XFS_BLI_DIRTY);
bip->__bli_format.blf_flags &= ~XFS_BLF_INODE_BUF;
bip->__bli_format.blf_flags |= XFS_BLF_CANCEL;
bip->__bli_format.blf_flags &= ~XFS_BLFT_MASK;
for (i = 0; i < bip->bli_format_count; i++) {
memset(bip->bli_formats[i].blf_data_map, 0,
(bip->bli_formats[i].blf_map_size * sizeof(uint)));
}
set_bit(XFS_LI_DIRTY, &bip->bli_item.li_flags);
tp->t_flags |= XFS_TRANS_DIRTY;
}
/*
xfs: Ensure inode allocation buffers are fully replayed With delayed logging, we can get inode allocation buffers in the same transaction inode unlink buffers. We don't currently mark inode allocation buffers in the log, so inode unlink buffers take precedence over allocation buffers. The result is that when they are combined into the same checkpoint, only the unlinked inode chain fields are replayed, resulting in uninitialised inode buffers being detected when the next inode modification is replayed. To fix this, we need to ensure that we do not set the inode buffer flag in the buffer log item format flags if the inode allocation has not already hit the log. To avoid requiring a change to log recovery, we really need to make this a modification that relies only on in-memory sate. We can do this by checking during buffer log formatting (while the CIL cannot be flushed) if we are still in the same sequence when we commit the unlink transaction as the inode allocation transaction. If we are, then we do not add the inode buffer flag to the buffer log format item flags. This means the entire buffer will be replayed, not just the unlinked fields. We do this while CIL flusheѕ are locked out to ensure that we don't race with the sequence numbers changing and hence fail to put the inode buffer flag in the buffer format flags when we really need to. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Alex Elder <aelder@sgi.com>
2010-05-20 21:19:42 +08:00
* This call is used to indicate that the buffer contains on-disk inodes which
* must be handled specially during recovery. They require special handling
* because only the di_next_unlinked from the inodes in the buffer should be
* recovered. The rest of the data in the buffer is logged via the inodes
* themselves.
*
xfs: Ensure inode allocation buffers are fully replayed With delayed logging, we can get inode allocation buffers in the same transaction inode unlink buffers. We don't currently mark inode allocation buffers in the log, so inode unlink buffers take precedence over allocation buffers. The result is that when they are combined into the same checkpoint, only the unlinked inode chain fields are replayed, resulting in uninitialised inode buffers being detected when the next inode modification is replayed. To fix this, we need to ensure that we do not set the inode buffer flag in the buffer log item format flags if the inode allocation has not already hit the log. To avoid requiring a change to log recovery, we really need to make this a modification that relies only on in-memory sate. We can do this by checking during buffer log formatting (while the CIL cannot be flushed) if we are still in the same sequence when we commit the unlink transaction as the inode allocation transaction. If we are, then we do not add the inode buffer flag to the buffer log format item flags. This means the entire buffer will be replayed, not just the unlinked fields. We do this while CIL flusheѕ are locked out to ensure that we don't race with the sequence numbers changing and hence fail to put the inode buffer flag in the buffer format flags when we really need to. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Alex Elder <aelder@sgi.com>
2010-05-20 21:19:42 +08:00
* All we do is set the XFS_BLI_INODE_BUF flag in the items flags so it can be
* transferred to the buffer's log format structure so that we'll know what to
* do at recovery time.
*/
void
xfs_trans_inode_buf(
xfs_trans_t *tp,
xfs_buf_t *bp)
{
struct xfs_buf_log_item *bip = bp->b_log_item;
ASSERT(bp->b_transp == tp);
ASSERT(bip != NULL);
ASSERT(atomic_read(&bip->bli_refcount) > 0);
xfs: Ensure inode allocation buffers are fully replayed With delayed logging, we can get inode allocation buffers in the same transaction inode unlink buffers. We don't currently mark inode allocation buffers in the log, so inode unlink buffers take precedence over allocation buffers. The result is that when they are combined into the same checkpoint, only the unlinked inode chain fields are replayed, resulting in uninitialised inode buffers being detected when the next inode modification is replayed. To fix this, we need to ensure that we do not set the inode buffer flag in the buffer log item format flags if the inode allocation has not already hit the log. To avoid requiring a change to log recovery, we really need to make this a modification that relies only on in-memory sate. We can do this by checking during buffer log formatting (while the CIL cannot be flushed) if we are still in the same sequence when we commit the unlink transaction as the inode allocation transaction. If we are, then we do not add the inode buffer flag to the buffer log format item flags. This means the entire buffer will be replayed, not just the unlinked fields. We do this while CIL flusheѕ are locked out to ensure that we don't race with the sequence numbers changing and hence fail to put the inode buffer flag in the buffer format flags when we really need to. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Alex Elder <aelder@sgi.com>
2010-05-20 21:19:42 +08:00
bip->bli_flags |= XFS_BLI_INODE_BUF;
bp->b_flags |= _XBF_INODES;
xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DINO_BUF);
}
/*
* This call is used to indicate that the buffer is going to
* be staled and was an inode buffer. This means it gets
* special processing during unpin - where any inodes
* associated with the buffer should be removed from ail.
* There is also special processing during recovery,
* any replay of the inodes in the buffer needs to be
* prevented as the buffer may have been reused.
*/
void
xfs_trans_stale_inode_buf(
xfs_trans_t *tp,
xfs_buf_t *bp)
{
struct xfs_buf_log_item *bip = bp->b_log_item;
ASSERT(bp->b_transp == tp);
ASSERT(bip != NULL);
ASSERT(atomic_read(&bip->bli_refcount) > 0);
bip->bli_flags |= XFS_BLI_STALE_INODE;
bp->b_flags |= _XBF_INODES;
xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DINO_BUF);
}
/*
* Mark the buffer as being one which contains newly allocated
* inodes. We need to make sure that even if this buffer is
* relogged as an 'inode buf' we still recover all of the inode
* images in the face of a crash. This works in coordination with
* xfs_buf_item_committed() to ensure that the buffer remains in the
* AIL at its original location even after it has been relogged.
*/
/* ARGSUSED */
void
xfs_trans_inode_alloc_buf(
xfs_trans_t *tp,
xfs_buf_t *bp)
{
struct xfs_buf_log_item *bip = bp->b_log_item;
ASSERT(bp->b_transp == tp);
ASSERT(bip != NULL);
ASSERT(atomic_read(&bip->bli_refcount) > 0);
bip->bli_flags |= XFS_BLI_INODE_ALLOC_BUF;
bp->b_flags |= _XBF_INODES;
xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DINO_BUF);
}
/*
* Mark the buffer as ordered for this transaction. This means that the contents
* of the buffer are not recorded in the transaction but it is tracked in the
* AIL as though it was. This allows us to record logical changes in
* transactions rather than the physical changes we make to the buffer without
* changing writeback ordering constraints of metadata buffers.
*/
xfs: disallow marking previously dirty buffers as ordered Ordered buffers are used in situations where the buffer is not physically logged but must pass through the transaction/logging pipeline for a particular transaction. As a result, ordered buffers are not unpinned and written back until the transaction commits to the log. Ordered buffers have a strict requirement that the target buffer must not be currently dirty and resident in the log pipeline at the time it is marked ordered. If a dirty+ordered buffer is committed, the buffer is reinserted to the AIL but not physically relogged at the LSN of the associated checkpoint. The buffer log item is assigned the LSN of the latest checkpoint and the AIL effectively releases the previously logged buffer content from the active log before the buffer has been written back. If the tail pushes forward and a filesystem crash occurs while in this state, an inconsistent filesystem could result. It is currently the caller responsibility to ensure an ordered buffer is not already dirty from a previous modification. This is unclear and error prone when not used in situations where it is guaranteed a buffer has not been previously modified (such as new metadata allocations). To facilitate general purpose use of ordered buffers, update xfs_trans_ordered_buf() to conditionally order the buffer based on state of the log item and return the status of the result. If the bli is dirty, do not order the buffer and return false. The caller must either physically log the buffer (having acquired the appropriate log reservation) or push it from the AIL to clean it before it can be marked ordered in the current transaction. Note that ordered buffers are currently only used in two situations: 1.) inode chunk allocation where previously logged buffers are not possible and 2.) extent swap which will be updated to handle ordered buffer failures in a separate patch. Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2017-08-30 01:08:40 +08:00
bool
xfs_trans_ordered_buf(
struct xfs_trans *tp,
struct xfs_buf *bp)
{
struct xfs_buf_log_item *bip = bp->b_log_item;
ASSERT(bp->b_transp == tp);
ASSERT(bip != NULL);
ASSERT(atomic_read(&bip->bli_refcount) > 0);
xfs: disallow marking previously dirty buffers as ordered Ordered buffers are used in situations where the buffer is not physically logged but must pass through the transaction/logging pipeline for a particular transaction. As a result, ordered buffers are not unpinned and written back until the transaction commits to the log. Ordered buffers have a strict requirement that the target buffer must not be currently dirty and resident in the log pipeline at the time it is marked ordered. If a dirty+ordered buffer is committed, the buffer is reinserted to the AIL but not physically relogged at the LSN of the associated checkpoint. The buffer log item is assigned the LSN of the latest checkpoint and the AIL effectively releases the previously logged buffer content from the active log before the buffer has been written back. If the tail pushes forward and a filesystem crash occurs while in this state, an inconsistent filesystem could result. It is currently the caller responsibility to ensure an ordered buffer is not already dirty from a previous modification. This is unclear and error prone when not used in situations where it is guaranteed a buffer has not been previously modified (such as new metadata allocations). To facilitate general purpose use of ordered buffers, update xfs_trans_ordered_buf() to conditionally order the buffer based on state of the log item and return the status of the result. If the bli is dirty, do not order the buffer and return false. The caller must either physically log the buffer (having acquired the appropriate log reservation) or push it from the AIL to clean it before it can be marked ordered in the current transaction. Note that ordered buffers are currently only used in two situations: 1.) inode chunk allocation where previously logged buffers are not possible and 2.) extent swap which will be updated to handle ordered buffer failures in a separate patch. Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2017-08-30 01:08:40 +08:00
if (xfs_buf_item_dirty_format(bip))
return false;
bip->bli_flags |= XFS_BLI_ORDERED;
trace_xfs_buf_item_ordered(bip);
/*
* We don't log a dirty range of an ordered buffer but it still needs
* to be marked dirty and that it has been logged.
*/
xfs_trans_dirty_buf(tp, bp);
xfs: disallow marking previously dirty buffers as ordered Ordered buffers are used in situations where the buffer is not physically logged but must pass through the transaction/logging pipeline for a particular transaction. As a result, ordered buffers are not unpinned and written back until the transaction commits to the log. Ordered buffers have a strict requirement that the target buffer must not be currently dirty and resident in the log pipeline at the time it is marked ordered. If a dirty+ordered buffer is committed, the buffer is reinserted to the AIL but not physically relogged at the LSN of the associated checkpoint. The buffer log item is assigned the LSN of the latest checkpoint and the AIL effectively releases the previously logged buffer content from the active log before the buffer has been written back. If the tail pushes forward and a filesystem crash occurs while in this state, an inconsistent filesystem could result. It is currently the caller responsibility to ensure an ordered buffer is not already dirty from a previous modification. This is unclear and error prone when not used in situations where it is guaranteed a buffer has not been previously modified (such as new metadata allocations). To facilitate general purpose use of ordered buffers, update xfs_trans_ordered_buf() to conditionally order the buffer based on state of the log item and return the status of the result. If the bli is dirty, do not order the buffer and return false. The caller must either physically log the buffer (having acquired the appropriate log reservation) or push it from the AIL to clean it before it can be marked ordered in the current transaction. Note that ordered buffers are currently only used in two situations: 1.) inode chunk allocation where previously logged buffers are not possible and 2.) extent swap which will be updated to handle ordered buffer failures in a separate patch. Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2017-08-30 01:08:40 +08:00
return true;
}
/*
* Set the type of the buffer for log recovery so that it can correctly identify
* and hence attach the correct buffer ops to the buffer after replay.
*/
void
xfs_trans_buf_set_type(
struct xfs_trans *tp,
struct xfs_buf *bp,
enum xfs_blft type)
{
struct xfs_buf_log_item *bip = bp->b_log_item;
if (!tp)
return;
ASSERT(bp->b_transp == tp);
ASSERT(bip != NULL);
ASSERT(atomic_read(&bip->bli_refcount) > 0);
xfs_blft_to_flags(&bip->__bli_format, type);
}
void
xfs_trans_buf_copy_type(
struct xfs_buf *dst_bp,
struct xfs_buf *src_bp)
{
struct xfs_buf_log_item *sbip = src_bp->b_log_item;
struct xfs_buf_log_item *dbip = dst_bp->b_log_item;
enum xfs_blft type;
type = xfs_blft_from_flags(&sbip->__bli_format);
xfs_blft_to_flags(&dbip->__bli_format, type);
}
/*
* Similar to xfs_trans_inode_buf(), this marks the buffer as a cluster of
* dquots. However, unlike in inode buffer recovery, dquot buffers get
* recovered in their entirety. (Hence, no XFS_BLI_DQUOT_ALLOC_BUF flag).
* The only thing that makes dquot buffers different from regular
* buffers is that we must not replay dquot bufs when recovering
* if a _corresponding_ quotaoff has happened. We also have to distinguish
* between usr dquot bufs and grp dquot bufs, because usr and grp quotas
* can be turned off independently.
*/
/* ARGSUSED */
void
xfs_trans_dquot_buf(
xfs_trans_t *tp,
xfs_buf_t *bp,
uint type)
{
struct xfs_buf_log_item *bip = bp->b_log_item;
ASSERT(type == XFS_BLF_UDQUOT_BUF ||
type == XFS_BLF_PDQUOT_BUF ||
type == XFS_BLF_GDQUOT_BUF);
bip->__bli_format.blf_flags |= type;
switch (type) {
case XFS_BLF_UDQUOT_BUF:
type = XFS_BLFT_UDQUOT_BUF;
break;
case XFS_BLF_PDQUOT_BUF:
type = XFS_BLFT_PDQUOT_BUF;
break;
case XFS_BLF_GDQUOT_BUF:
type = XFS_BLFT_GDQUOT_BUF;
break;
default:
type = XFS_BLFT_UNKNOWN_BUF;
break;
}
bp->b_flags |= _XBF_DQUOTS;
xfs_trans_buf_set_type(tp, bp, type);
}