mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-25 00:20:53 +07:00
fc0561cefc
xfs: timestamp updates cause excessive fdatasync log traffic Sage Weil reported that a ceph test workload was writing to the log on every fdatasync during an overwrite workload. Event tracing showed that the only metadata modification being made was the timestamp updates during the write(2) syscall, but fdatasync(2) is supposed to ignore them. The key observation was that the transactions in the log all looked like this: INODE: #regs: 4 ino: 0x8b flags: 0x45 dsize: 32 And contained a flags field of 0x45 or 0x85, and had data and attribute forks following the inode core. This means that the timestamp updates were triggering dirty relogging of previously logged parts of the inode that hadn't yet been flushed back to disk. There are two parts to this problem. The first is that XFS relogs dirty regions in subsequent transactions, so it carries around the fields that have been dirtied since the last time the inode was written back to disk, not since the last time the inode was forced into the log. The second part is that on v5 filesystems, the inode change count update during inode dirtying also sets the XFS_ILOG_CORE flag, so on v5 filesystems this makes a timestamp update dirty the entire inode. As a result when fdatasync is run, it looks at the dirty fields in the inode, and sees more than just the timestamp flag, even though the only metadata change since the last fdatasync was just the timestamps. Hence we force the log on every subsequent fdatasync even though it is not needed. To fix this, add a new field to the inode log item that tracks changes since the last time fsync/fdatasync forced the log to flush the changes to the journal. This flag is updated when we dirty the inode, but we do it before updating the change count so it does not carry the "core dirty" flag from timestamp updates. The fields are zeroed when the inode is marked clean (due to writeback/freeing) or when an fsync/datasync forces the log. Hence if we only dirty the timestamps on the inode between fsync/fdatasync calls, the fdatasync will not trigger another log force. Over 100 runs of the test program: Ext4 baseline: runtime: 1.63s +/- 0.24s avg lat: 1.59ms +/- 0.24ms iops: ~2000 XFS, vanilla kernel: runtime: 2.45s +/- 0.18s avg lat: 2.39ms +/- 0.18ms log forces: ~400/s iops: ~1000 XFS, patched kernel: runtime: 1.49s +/- 0.26s avg lat: 1.46ms +/- 0.25ms log forces: ~30/s iops: ~1500 Reported-by: Sage Weil <sage@redhat.com> Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
784 lines
21 KiB
C
784 lines
21 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
|
|
*/
|
|
#include "xfs.h"
|
|
#include "xfs_fs.h"
|
|
#include "xfs_format.h"
|
|
#include "xfs_log_format.h"
|
|
#include "xfs_trans_resv.h"
|
|
#include "xfs_mount.h"
|
|
#include "xfs_inode.h"
|
|
#include "xfs_trans.h"
|
|
#include "xfs_inode_item.h"
|
|
#include "xfs_error.h"
|
|
#include "xfs_trace.h"
|
|
#include "xfs_trans_priv.h"
|
|
#include "xfs_log.h"
|
|
|
|
|
|
kmem_zone_t *xfs_ili_zone; /* inode log item zone */
|
|
|
|
static inline struct xfs_inode_log_item *INODE_ITEM(struct xfs_log_item *lip)
|
|
{
|
|
return container_of(lip, struct xfs_inode_log_item, ili_item);
|
|
}
|
|
|
|
STATIC void
|
|
xfs_inode_item_data_fork_size(
|
|
struct xfs_inode_log_item *iip,
|
|
int *nvecs,
|
|
int *nbytes)
|
|
{
|
|
struct xfs_inode *ip = iip->ili_inode;
|
|
|
|
switch (ip->i_d.di_format) {
|
|
case XFS_DINODE_FMT_EXTENTS:
|
|
if ((iip->ili_fields & XFS_ILOG_DEXT) &&
|
|
ip->i_d.di_nextents > 0 &&
|
|
ip->i_df.if_bytes > 0) {
|
|
/* worst case, doesn't subtract delalloc extents */
|
|
*nbytes += XFS_IFORK_DSIZE(ip);
|
|
*nvecs += 1;
|
|
}
|
|
break;
|
|
case XFS_DINODE_FMT_BTREE:
|
|
if ((iip->ili_fields & XFS_ILOG_DBROOT) &&
|
|
ip->i_df.if_broot_bytes > 0) {
|
|
*nbytes += ip->i_df.if_broot_bytes;
|
|
*nvecs += 1;
|
|
}
|
|
break;
|
|
case XFS_DINODE_FMT_LOCAL:
|
|
if ((iip->ili_fields & XFS_ILOG_DDATA) &&
|
|
ip->i_df.if_bytes > 0) {
|
|
*nbytes += roundup(ip->i_df.if_bytes, 4);
|
|
*nvecs += 1;
|
|
}
|
|
break;
|
|
|
|
case XFS_DINODE_FMT_DEV:
|
|
case XFS_DINODE_FMT_UUID:
|
|
break;
|
|
default:
|
|
ASSERT(0);
|
|
break;
|
|
}
|
|
}
|
|
|
|
STATIC void
|
|
xfs_inode_item_attr_fork_size(
|
|
struct xfs_inode_log_item *iip,
|
|
int *nvecs,
|
|
int *nbytes)
|
|
{
|
|
struct xfs_inode *ip = iip->ili_inode;
|
|
|
|
switch (ip->i_d.di_aformat) {
|
|
case XFS_DINODE_FMT_EXTENTS:
|
|
if ((iip->ili_fields & XFS_ILOG_AEXT) &&
|
|
ip->i_d.di_anextents > 0 &&
|
|
ip->i_afp->if_bytes > 0) {
|
|
/* worst case, doesn't subtract unused space */
|
|
*nbytes += XFS_IFORK_ASIZE(ip);
|
|
*nvecs += 1;
|
|
}
|
|
break;
|
|
case XFS_DINODE_FMT_BTREE:
|
|
if ((iip->ili_fields & XFS_ILOG_ABROOT) &&
|
|
ip->i_afp->if_broot_bytes > 0) {
|
|
*nbytes += ip->i_afp->if_broot_bytes;
|
|
*nvecs += 1;
|
|
}
|
|
break;
|
|
case XFS_DINODE_FMT_LOCAL:
|
|
if ((iip->ili_fields & XFS_ILOG_ADATA) &&
|
|
ip->i_afp->if_bytes > 0) {
|
|
*nbytes += roundup(ip->i_afp->if_bytes, 4);
|
|
*nvecs += 1;
|
|
}
|
|
break;
|
|
default:
|
|
ASSERT(0);
|
|
break;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* This returns the number of iovecs needed to log the given inode item.
|
|
*
|
|
* We need one iovec for the inode log format structure, one for the
|
|
* inode core, and possibly one for the inode data/extents/b-tree root
|
|
* and one for the inode attribute data/extents/b-tree root.
|
|
*/
|
|
STATIC void
|
|
xfs_inode_item_size(
|
|
struct xfs_log_item *lip,
|
|
int *nvecs,
|
|
int *nbytes)
|
|
{
|
|
struct xfs_inode_log_item *iip = INODE_ITEM(lip);
|
|
struct xfs_inode *ip = iip->ili_inode;
|
|
|
|
*nvecs += 2;
|
|
*nbytes += sizeof(struct xfs_inode_log_format) +
|
|
xfs_icdinode_size(ip->i_d.di_version);
|
|
|
|
xfs_inode_item_data_fork_size(iip, nvecs, nbytes);
|
|
if (XFS_IFORK_Q(ip))
|
|
xfs_inode_item_attr_fork_size(iip, nvecs, nbytes);
|
|
}
|
|
|
|
STATIC void
|
|
xfs_inode_item_format_data_fork(
|
|
struct xfs_inode_log_item *iip,
|
|
struct xfs_inode_log_format *ilf,
|
|
struct xfs_log_vec *lv,
|
|
struct xfs_log_iovec **vecp)
|
|
{
|
|
struct xfs_inode *ip = iip->ili_inode;
|
|
size_t data_bytes;
|
|
|
|
switch (ip->i_d.di_format) {
|
|
case XFS_DINODE_FMT_EXTENTS:
|
|
iip->ili_fields &=
|
|
~(XFS_ILOG_DDATA | XFS_ILOG_DBROOT |
|
|
XFS_ILOG_DEV | XFS_ILOG_UUID);
|
|
|
|
if ((iip->ili_fields & XFS_ILOG_DEXT) &&
|
|
ip->i_d.di_nextents > 0 &&
|
|
ip->i_df.if_bytes > 0) {
|
|
struct xfs_bmbt_rec *p;
|
|
|
|
ASSERT(ip->i_df.if_u1.if_extents != NULL);
|
|
ASSERT(ip->i_df.if_bytes / sizeof(xfs_bmbt_rec_t) > 0);
|
|
|
|
p = xlog_prepare_iovec(lv, vecp, XLOG_REG_TYPE_IEXT);
|
|
data_bytes = xfs_iextents_copy(ip, p, XFS_DATA_FORK);
|
|
xlog_finish_iovec(lv, *vecp, data_bytes);
|
|
|
|
ASSERT(data_bytes <= ip->i_df.if_bytes);
|
|
|
|
ilf->ilf_dsize = data_bytes;
|
|
ilf->ilf_size++;
|
|
} else {
|
|
iip->ili_fields &= ~XFS_ILOG_DEXT;
|
|
}
|
|
break;
|
|
case XFS_DINODE_FMT_BTREE:
|
|
iip->ili_fields &=
|
|
~(XFS_ILOG_DDATA | XFS_ILOG_DEXT |
|
|
XFS_ILOG_DEV | XFS_ILOG_UUID);
|
|
|
|
if ((iip->ili_fields & XFS_ILOG_DBROOT) &&
|
|
ip->i_df.if_broot_bytes > 0) {
|
|
ASSERT(ip->i_df.if_broot != NULL);
|
|
xlog_copy_iovec(lv, vecp, XLOG_REG_TYPE_IBROOT,
|
|
ip->i_df.if_broot,
|
|
ip->i_df.if_broot_bytes);
|
|
ilf->ilf_dsize = ip->i_df.if_broot_bytes;
|
|
ilf->ilf_size++;
|
|
} else {
|
|
ASSERT(!(iip->ili_fields &
|
|
XFS_ILOG_DBROOT));
|
|
iip->ili_fields &= ~XFS_ILOG_DBROOT;
|
|
}
|
|
break;
|
|
case XFS_DINODE_FMT_LOCAL:
|
|
iip->ili_fields &=
|
|
~(XFS_ILOG_DEXT | XFS_ILOG_DBROOT |
|
|
XFS_ILOG_DEV | XFS_ILOG_UUID);
|
|
if ((iip->ili_fields & XFS_ILOG_DDATA) &&
|
|
ip->i_df.if_bytes > 0) {
|
|
/*
|
|
* Round i_bytes up to a word boundary.
|
|
* The underlying memory is guaranteed to
|
|
* to be there by xfs_idata_realloc().
|
|
*/
|
|
data_bytes = roundup(ip->i_df.if_bytes, 4);
|
|
ASSERT(ip->i_df.if_real_bytes == 0 ||
|
|
ip->i_df.if_real_bytes == data_bytes);
|
|
ASSERT(ip->i_df.if_u1.if_data != NULL);
|
|
ASSERT(ip->i_d.di_size > 0);
|
|
xlog_copy_iovec(lv, vecp, XLOG_REG_TYPE_ILOCAL,
|
|
ip->i_df.if_u1.if_data, data_bytes);
|
|
ilf->ilf_dsize = (unsigned)data_bytes;
|
|
ilf->ilf_size++;
|
|
} else {
|
|
iip->ili_fields &= ~XFS_ILOG_DDATA;
|
|
}
|
|
break;
|
|
case XFS_DINODE_FMT_DEV:
|
|
iip->ili_fields &=
|
|
~(XFS_ILOG_DDATA | XFS_ILOG_DBROOT |
|
|
XFS_ILOG_DEXT | XFS_ILOG_UUID);
|
|
if (iip->ili_fields & XFS_ILOG_DEV)
|
|
ilf->ilf_u.ilfu_rdev = ip->i_df.if_u2.if_rdev;
|
|
break;
|
|
case XFS_DINODE_FMT_UUID:
|
|
iip->ili_fields &=
|
|
~(XFS_ILOG_DDATA | XFS_ILOG_DBROOT |
|
|
XFS_ILOG_DEXT | XFS_ILOG_DEV);
|
|
if (iip->ili_fields & XFS_ILOG_UUID)
|
|
ilf->ilf_u.ilfu_uuid = ip->i_df.if_u2.if_uuid;
|
|
break;
|
|
default:
|
|
ASSERT(0);
|
|
break;
|
|
}
|
|
}
|
|
|
|
STATIC void
|
|
xfs_inode_item_format_attr_fork(
|
|
struct xfs_inode_log_item *iip,
|
|
struct xfs_inode_log_format *ilf,
|
|
struct xfs_log_vec *lv,
|
|
struct xfs_log_iovec **vecp)
|
|
{
|
|
struct xfs_inode *ip = iip->ili_inode;
|
|
size_t data_bytes;
|
|
|
|
switch (ip->i_d.di_aformat) {
|
|
case XFS_DINODE_FMT_EXTENTS:
|
|
iip->ili_fields &=
|
|
~(XFS_ILOG_ADATA | XFS_ILOG_ABROOT);
|
|
|
|
if ((iip->ili_fields & XFS_ILOG_AEXT) &&
|
|
ip->i_d.di_anextents > 0 &&
|
|
ip->i_afp->if_bytes > 0) {
|
|
struct xfs_bmbt_rec *p;
|
|
|
|
ASSERT(ip->i_afp->if_bytes / sizeof(xfs_bmbt_rec_t) ==
|
|
ip->i_d.di_anextents);
|
|
ASSERT(ip->i_afp->if_u1.if_extents != NULL);
|
|
|
|
p = xlog_prepare_iovec(lv, vecp, XLOG_REG_TYPE_IATTR_EXT);
|
|
data_bytes = xfs_iextents_copy(ip, p, XFS_ATTR_FORK);
|
|
xlog_finish_iovec(lv, *vecp, data_bytes);
|
|
|
|
ilf->ilf_asize = data_bytes;
|
|
ilf->ilf_size++;
|
|
} else {
|
|
iip->ili_fields &= ~XFS_ILOG_AEXT;
|
|
}
|
|
break;
|
|
case XFS_DINODE_FMT_BTREE:
|
|
iip->ili_fields &=
|
|
~(XFS_ILOG_ADATA | XFS_ILOG_AEXT);
|
|
|
|
if ((iip->ili_fields & XFS_ILOG_ABROOT) &&
|
|
ip->i_afp->if_broot_bytes > 0) {
|
|
ASSERT(ip->i_afp->if_broot != NULL);
|
|
|
|
xlog_copy_iovec(lv, vecp, XLOG_REG_TYPE_IATTR_BROOT,
|
|
ip->i_afp->if_broot,
|
|
ip->i_afp->if_broot_bytes);
|
|
ilf->ilf_asize = ip->i_afp->if_broot_bytes;
|
|
ilf->ilf_size++;
|
|
} else {
|
|
iip->ili_fields &= ~XFS_ILOG_ABROOT;
|
|
}
|
|
break;
|
|
case XFS_DINODE_FMT_LOCAL:
|
|
iip->ili_fields &=
|
|
~(XFS_ILOG_AEXT | XFS_ILOG_ABROOT);
|
|
|
|
if ((iip->ili_fields & XFS_ILOG_ADATA) &&
|
|
ip->i_afp->if_bytes > 0) {
|
|
/*
|
|
* Round i_bytes up to a word boundary.
|
|
* The underlying memory is guaranteed to
|
|
* to be there by xfs_idata_realloc().
|
|
*/
|
|
data_bytes = roundup(ip->i_afp->if_bytes, 4);
|
|
ASSERT(ip->i_afp->if_real_bytes == 0 ||
|
|
ip->i_afp->if_real_bytes == data_bytes);
|
|
ASSERT(ip->i_afp->if_u1.if_data != NULL);
|
|
xlog_copy_iovec(lv, vecp, XLOG_REG_TYPE_IATTR_LOCAL,
|
|
ip->i_afp->if_u1.if_data,
|
|
data_bytes);
|
|
ilf->ilf_asize = (unsigned)data_bytes;
|
|
ilf->ilf_size++;
|
|
} else {
|
|
iip->ili_fields &= ~XFS_ILOG_ADATA;
|
|
}
|
|
break;
|
|
default:
|
|
ASSERT(0);
|
|
break;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* This is called to fill in the vector of log iovecs for the given inode
|
|
* log item. It fills the first item with an inode log format structure,
|
|
* the second with the on-disk inode structure, and a possible third and/or
|
|
* fourth with the inode data/extents/b-tree root and inode attributes
|
|
* data/extents/b-tree root.
|
|
*/
|
|
STATIC void
|
|
xfs_inode_item_format(
|
|
struct xfs_log_item *lip,
|
|
struct xfs_log_vec *lv)
|
|
{
|
|
struct xfs_inode_log_item *iip = INODE_ITEM(lip);
|
|
struct xfs_inode *ip = iip->ili_inode;
|
|
struct xfs_inode_log_format *ilf;
|
|
struct xfs_log_iovec *vecp = NULL;
|
|
|
|
ASSERT(ip->i_d.di_version > 1);
|
|
|
|
ilf = xlog_prepare_iovec(lv, &vecp, XLOG_REG_TYPE_IFORMAT);
|
|
ilf->ilf_type = XFS_LI_INODE;
|
|
ilf->ilf_ino = ip->i_ino;
|
|
ilf->ilf_blkno = ip->i_imap.im_blkno;
|
|
ilf->ilf_len = ip->i_imap.im_len;
|
|
ilf->ilf_boffset = ip->i_imap.im_boffset;
|
|
ilf->ilf_fields = XFS_ILOG_CORE;
|
|
ilf->ilf_size = 2; /* format + core */
|
|
xlog_finish_iovec(lv, vecp, sizeof(struct xfs_inode_log_format));
|
|
|
|
xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_ICORE,
|
|
&ip->i_d,
|
|
xfs_icdinode_size(ip->i_d.di_version));
|
|
|
|
xfs_inode_item_format_data_fork(iip, ilf, lv, &vecp);
|
|
if (XFS_IFORK_Q(ip)) {
|
|
xfs_inode_item_format_attr_fork(iip, ilf, lv, &vecp);
|
|
} else {
|
|
iip->ili_fields &=
|
|
~(XFS_ILOG_ADATA | XFS_ILOG_ABROOT | XFS_ILOG_AEXT);
|
|
}
|
|
|
|
/* update the format with the exact fields we actually logged */
|
|
ilf->ilf_fields |= (iip->ili_fields & ~XFS_ILOG_TIMESTAMP);
|
|
}
|
|
|
|
/*
|
|
* This is called to pin the inode associated with the inode log
|
|
* item in memory so it cannot be written out.
|
|
*/
|
|
STATIC void
|
|
xfs_inode_item_pin(
|
|
struct xfs_log_item *lip)
|
|
{
|
|
struct xfs_inode *ip = INODE_ITEM(lip)->ili_inode;
|
|
|
|
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
|
|
|
|
trace_xfs_inode_pin(ip, _RET_IP_);
|
|
atomic_inc(&ip->i_pincount);
|
|
}
|
|
|
|
|
|
/*
|
|
* This is called to unpin the inode associated with the inode log
|
|
* item which was previously pinned with a call to xfs_inode_item_pin().
|
|
*
|
|
* Also wake up anyone in xfs_iunpin_wait() if the count goes to 0.
|
|
*/
|
|
STATIC void
|
|
xfs_inode_item_unpin(
|
|
struct xfs_log_item *lip,
|
|
int remove)
|
|
{
|
|
struct xfs_inode *ip = INODE_ITEM(lip)->ili_inode;
|
|
|
|
trace_xfs_inode_unpin(ip, _RET_IP_);
|
|
ASSERT(atomic_read(&ip->i_pincount) > 0);
|
|
if (atomic_dec_and_test(&ip->i_pincount))
|
|
wake_up_bit(&ip->i_flags, __XFS_IPINNED_BIT);
|
|
}
|
|
|
|
STATIC uint
|
|
xfs_inode_item_push(
|
|
struct xfs_log_item *lip,
|
|
struct list_head *buffer_list)
|
|
{
|
|
struct xfs_inode_log_item *iip = INODE_ITEM(lip);
|
|
struct xfs_inode *ip = iip->ili_inode;
|
|
struct xfs_buf *bp = NULL;
|
|
uint rval = XFS_ITEM_SUCCESS;
|
|
int error;
|
|
|
|
if (xfs_ipincount(ip) > 0)
|
|
return XFS_ITEM_PINNED;
|
|
|
|
if (!xfs_ilock_nowait(ip, XFS_ILOCK_SHARED))
|
|
return XFS_ITEM_LOCKED;
|
|
|
|
/*
|
|
* Re-check the pincount now that we stabilized the value by
|
|
* taking the ilock.
|
|
*/
|
|
if (xfs_ipincount(ip) > 0) {
|
|
rval = XFS_ITEM_PINNED;
|
|
goto out_unlock;
|
|
}
|
|
|
|
/*
|
|
* Stale inode items should force out the iclog.
|
|
*/
|
|
if (ip->i_flags & XFS_ISTALE) {
|
|
rval = XFS_ITEM_PINNED;
|
|
goto out_unlock;
|
|
}
|
|
|
|
/*
|
|
* Someone else is already flushing the inode. Nothing we can do
|
|
* here but wait for the flush to finish and remove the item from
|
|
* the AIL.
|
|
*/
|
|
if (!xfs_iflock_nowait(ip)) {
|
|
rval = XFS_ITEM_FLUSHING;
|
|
goto out_unlock;
|
|
}
|
|
|
|
ASSERT(iip->ili_fields != 0 || XFS_FORCED_SHUTDOWN(ip->i_mount));
|
|
ASSERT(iip->ili_logged == 0 || XFS_FORCED_SHUTDOWN(ip->i_mount));
|
|
|
|
spin_unlock(&lip->li_ailp->xa_lock);
|
|
|
|
error = xfs_iflush(ip, &bp);
|
|
if (!error) {
|
|
if (!xfs_buf_delwri_queue(bp, buffer_list))
|
|
rval = XFS_ITEM_FLUSHING;
|
|
xfs_buf_relse(bp);
|
|
}
|
|
|
|
spin_lock(&lip->li_ailp->xa_lock);
|
|
out_unlock:
|
|
xfs_iunlock(ip, XFS_ILOCK_SHARED);
|
|
return rval;
|
|
}
|
|
|
|
/*
|
|
* Unlock the inode associated with the inode log item.
|
|
* Clear the fields of the inode and inode log item that
|
|
* are specific to the current transaction. If the
|
|
* hold flags is set, do not unlock the inode.
|
|
*/
|
|
STATIC void
|
|
xfs_inode_item_unlock(
|
|
struct xfs_log_item *lip)
|
|
{
|
|
struct xfs_inode_log_item *iip = INODE_ITEM(lip);
|
|
struct xfs_inode *ip = iip->ili_inode;
|
|
unsigned short lock_flags;
|
|
|
|
ASSERT(ip->i_itemp != NULL);
|
|
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
|
|
|
|
lock_flags = iip->ili_lock_flags;
|
|
iip->ili_lock_flags = 0;
|
|
if (lock_flags)
|
|
xfs_iunlock(ip, lock_flags);
|
|
}
|
|
|
|
/*
|
|
* This is called to find out where the oldest active copy of the inode log
|
|
* item in the on disk log resides now that the last log write of it completed
|
|
* at the given lsn. Since we always re-log all dirty data in an inode, the
|
|
* latest copy in the on disk log is the only one that matters. Therefore,
|
|
* simply return the given lsn.
|
|
*
|
|
* If the inode has been marked stale because the cluster is being freed, we
|
|
* don't want to (re-)insert this inode into the AIL. There is a race condition
|
|
* where the cluster buffer may be unpinned before the inode is inserted into
|
|
* the AIL during transaction committed processing. If the buffer is unpinned
|
|
* before the inode item has been committed and inserted, then it is possible
|
|
* for the buffer to be written and IO completes before the inode is inserted
|
|
* into the AIL. In that case, we'd be inserting a clean, stale inode into the
|
|
* AIL which will never get removed. It will, however, get reclaimed which
|
|
* triggers an assert in xfs_inode_free() complaining about freein an inode
|
|
* still in the AIL.
|
|
*
|
|
* To avoid this, just unpin the inode directly and return a LSN of -1 so the
|
|
* transaction committed code knows that it does not need to do any further
|
|
* processing on the item.
|
|
*/
|
|
STATIC xfs_lsn_t
|
|
xfs_inode_item_committed(
|
|
struct xfs_log_item *lip,
|
|
xfs_lsn_t lsn)
|
|
{
|
|
struct xfs_inode_log_item *iip = INODE_ITEM(lip);
|
|
struct xfs_inode *ip = iip->ili_inode;
|
|
|
|
if (xfs_iflags_test(ip, XFS_ISTALE)) {
|
|
xfs_inode_item_unpin(lip, 0);
|
|
return -1;
|
|
}
|
|
return lsn;
|
|
}
|
|
|
|
/*
|
|
* XXX rcc - this one really has to do something. Probably needs
|
|
* to stamp in a new field in the incore inode.
|
|
*/
|
|
STATIC void
|
|
xfs_inode_item_committing(
|
|
struct xfs_log_item *lip,
|
|
xfs_lsn_t lsn)
|
|
{
|
|
INODE_ITEM(lip)->ili_last_lsn = lsn;
|
|
}
|
|
|
|
/*
|
|
* This is the ops vector shared by all buf log items.
|
|
*/
|
|
static const struct xfs_item_ops xfs_inode_item_ops = {
|
|
.iop_size = xfs_inode_item_size,
|
|
.iop_format = xfs_inode_item_format,
|
|
.iop_pin = xfs_inode_item_pin,
|
|
.iop_unpin = xfs_inode_item_unpin,
|
|
.iop_unlock = xfs_inode_item_unlock,
|
|
.iop_committed = xfs_inode_item_committed,
|
|
.iop_push = xfs_inode_item_push,
|
|
.iop_committing = xfs_inode_item_committing
|
|
};
|
|
|
|
|
|
/*
|
|
* Initialize the inode log item for a newly allocated (in-core) inode.
|
|
*/
|
|
void
|
|
xfs_inode_item_init(
|
|
struct xfs_inode *ip,
|
|
struct xfs_mount *mp)
|
|
{
|
|
struct xfs_inode_log_item *iip;
|
|
|
|
ASSERT(ip->i_itemp == NULL);
|
|
iip = ip->i_itemp = kmem_zone_zalloc(xfs_ili_zone, KM_SLEEP);
|
|
|
|
iip->ili_inode = ip;
|
|
xfs_log_item_init(mp, &iip->ili_item, XFS_LI_INODE,
|
|
&xfs_inode_item_ops);
|
|
}
|
|
|
|
/*
|
|
* Free the inode log item and any memory hanging off of it.
|
|
*/
|
|
void
|
|
xfs_inode_item_destroy(
|
|
xfs_inode_t *ip)
|
|
{
|
|
kmem_zone_free(xfs_ili_zone, ip->i_itemp);
|
|
}
|
|
|
|
|
|
/*
|
|
* This is the inode flushing I/O completion routine. It is called
|
|
* from interrupt level when the buffer containing the inode is
|
|
* flushed to disk. It is responsible for removing the inode item
|
|
* from the AIL if it has not been re-logged, and unlocking the inode's
|
|
* flush lock.
|
|
*
|
|
* To reduce AIL lock traffic as much as possible, we scan the buffer log item
|
|
* list for other inodes that will run this function. We remove them from the
|
|
* buffer list so we can process all the inode IO completions in one AIL lock
|
|
* traversal.
|
|
*/
|
|
void
|
|
xfs_iflush_done(
|
|
struct xfs_buf *bp,
|
|
struct xfs_log_item *lip)
|
|
{
|
|
struct xfs_inode_log_item *iip;
|
|
struct xfs_log_item *blip;
|
|
struct xfs_log_item *next;
|
|
struct xfs_log_item *prev;
|
|
struct xfs_ail *ailp = lip->li_ailp;
|
|
int need_ail = 0;
|
|
|
|
/*
|
|
* Scan the buffer IO completions for other inodes being completed and
|
|
* attach them to the current inode log item.
|
|
*/
|
|
blip = bp->b_fspriv;
|
|
prev = NULL;
|
|
while (blip != NULL) {
|
|
if (blip->li_cb != xfs_iflush_done) {
|
|
prev = blip;
|
|
blip = blip->li_bio_list;
|
|
continue;
|
|
}
|
|
|
|
/* remove from list */
|
|
next = blip->li_bio_list;
|
|
if (!prev) {
|
|
bp->b_fspriv = next;
|
|
} else {
|
|
prev->li_bio_list = next;
|
|
}
|
|
|
|
/* add to current list */
|
|
blip->li_bio_list = lip->li_bio_list;
|
|
lip->li_bio_list = blip;
|
|
|
|
/*
|
|
* while we have the item, do the unlocked check for needing
|
|
* the AIL lock.
|
|
*/
|
|
iip = INODE_ITEM(blip);
|
|
if (iip->ili_logged && blip->li_lsn == iip->ili_flush_lsn)
|
|
need_ail++;
|
|
|
|
blip = next;
|
|
}
|
|
|
|
/* make sure we capture the state of the initial inode. */
|
|
iip = INODE_ITEM(lip);
|
|
if (iip->ili_logged && lip->li_lsn == iip->ili_flush_lsn)
|
|
need_ail++;
|
|
|
|
/*
|
|
* We only want to pull the item from the AIL if it is
|
|
* actually there and its location in the log has not
|
|
* changed since we started the flush. Thus, we only bother
|
|
* if the ili_logged flag is set and the inode's lsn has not
|
|
* changed. First we check the lsn outside
|
|
* the lock since it's cheaper, and then we recheck while
|
|
* holding the lock before removing the inode from the AIL.
|
|
*/
|
|
if (need_ail) {
|
|
struct xfs_log_item *log_items[need_ail];
|
|
int i = 0;
|
|
spin_lock(&ailp->xa_lock);
|
|
for (blip = lip; blip; blip = blip->li_bio_list) {
|
|
iip = INODE_ITEM(blip);
|
|
if (iip->ili_logged &&
|
|
blip->li_lsn == iip->ili_flush_lsn) {
|
|
log_items[i++] = blip;
|
|
}
|
|
ASSERT(i <= need_ail);
|
|
}
|
|
/* xfs_trans_ail_delete_bulk() drops the AIL lock. */
|
|
xfs_trans_ail_delete_bulk(ailp, log_items, i,
|
|
SHUTDOWN_CORRUPT_INCORE);
|
|
}
|
|
|
|
|
|
/*
|
|
* clean up and unlock the flush lock now we are done. We can clear the
|
|
* ili_last_fields bits now that we know that the data corresponding to
|
|
* them is safely on disk.
|
|
*/
|
|
for (blip = lip; blip; blip = next) {
|
|
next = blip->li_bio_list;
|
|
blip->li_bio_list = NULL;
|
|
|
|
iip = INODE_ITEM(blip);
|
|
iip->ili_logged = 0;
|
|
iip->ili_last_fields = 0;
|
|
xfs_ifunlock(iip->ili_inode);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* This is the inode flushing abort routine. It is called from xfs_iflush when
|
|
* the filesystem is shutting down to clean up the inode state. It is
|
|
* responsible for removing the inode item from the AIL if it has not been
|
|
* re-logged, and unlocking the inode's flush lock.
|
|
*/
|
|
void
|
|
xfs_iflush_abort(
|
|
xfs_inode_t *ip,
|
|
bool stale)
|
|
{
|
|
xfs_inode_log_item_t *iip = ip->i_itemp;
|
|
|
|
if (iip) {
|
|
if (iip->ili_item.li_flags & XFS_LI_IN_AIL) {
|
|
xfs_trans_ail_remove(&iip->ili_item,
|
|
stale ? SHUTDOWN_LOG_IO_ERROR :
|
|
SHUTDOWN_CORRUPT_INCORE);
|
|
}
|
|
iip->ili_logged = 0;
|
|
/*
|
|
* Clear the ili_last_fields bits now that we know that the
|
|
* data corresponding to them is safely on disk.
|
|
*/
|
|
iip->ili_last_fields = 0;
|
|
/*
|
|
* Clear the inode logging fields so no more flushes are
|
|
* attempted.
|
|
*/
|
|
iip->ili_fields = 0;
|
|
iip->ili_fsync_fields = 0;
|
|
}
|
|
/*
|
|
* Release the inode's flush lock since we're done with it.
|
|
*/
|
|
xfs_ifunlock(ip);
|
|
}
|
|
|
|
void
|
|
xfs_istale_done(
|
|
struct xfs_buf *bp,
|
|
struct xfs_log_item *lip)
|
|
{
|
|
xfs_iflush_abort(INODE_ITEM(lip)->ili_inode, true);
|
|
}
|
|
|
|
/*
|
|
* convert an xfs_inode_log_format struct from either 32 or 64 bit versions
|
|
* (which can have different field alignments) to the native version
|
|
*/
|
|
int
|
|
xfs_inode_item_format_convert(
|
|
xfs_log_iovec_t *buf,
|
|
xfs_inode_log_format_t *in_f)
|
|
{
|
|
if (buf->i_len == sizeof(xfs_inode_log_format_32_t)) {
|
|
xfs_inode_log_format_32_t *in_f32 = buf->i_addr;
|
|
|
|
in_f->ilf_type = in_f32->ilf_type;
|
|
in_f->ilf_size = in_f32->ilf_size;
|
|
in_f->ilf_fields = in_f32->ilf_fields;
|
|
in_f->ilf_asize = in_f32->ilf_asize;
|
|
in_f->ilf_dsize = in_f32->ilf_dsize;
|
|
in_f->ilf_ino = in_f32->ilf_ino;
|
|
/* copy biggest field of ilf_u */
|
|
memcpy(in_f->ilf_u.ilfu_uuid.__u_bits,
|
|
in_f32->ilf_u.ilfu_uuid.__u_bits,
|
|
sizeof(uuid_t));
|
|
in_f->ilf_blkno = in_f32->ilf_blkno;
|
|
in_f->ilf_len = in_f32->ilf_len;
|
|
in_f->ilf_boffset = in_f32->ilf_boffset;
|
|
return 0;
|
|
} else if (buf->i_len == sizeof(xfs_inode_log_format_64_t)){
|
|
xfs_inode_log_format_64_t *in_f64 = buf->i_addr;
|
|
|
|
in_f->ilf_type = in_f64->ilf_type;
|
|
in_f->ilf_size = in_f64->ilf_size;
|
|
in_f->ilf_fields = in_f64->ilf_fields;
|
|
in_f->ilf_asize = in_f64->ilf_asize;
|
|
in_f->ilf_dsize = in_f64->ilf_dsize;
|
|
in_f->ilf_ino = in_f64->ilf_ino;
|
|
/* copy biggest field of ilf_u */
|
|
memcpy(in_f->ilf_u.ilfu_uuid.__u_bits,
|
|
in_f64->ilf_u.ilfu_uuid.__u_bits,
|
|
sizeof(uuid_t));
|
|
in_f->ilf_blkno = in_f64->ilf_blkno;
|
|
in_f->ilf_len = in_f64->ilf_len;
|
|
in_f->ilf_boffset = in_f64->ilf_boffset;
|
|
return 0;
|
|
}
|
|
return -EFSCORRUPTED;
|
|
}
|